57 results for “Safe”

ZTrust is a Python supply-chain scanner that checks manifests, lockfiles, source and GitHub workflows for vulnerable or malicious dependencies (via OSV.dev), typosquats, leaked secrets, unsafe lockfiles and risky CI patterns such as pwn requests and script injection. It outputs console, JSON and SARIF 2.1.0 and ships as a GitHub Action. It also includes a FastAPI bounty service using commit-reveal and shielded Zcash payouts for researchers.

github.comrepoAdded 27 Oct 2026, published 22 Oct 2026🛡️ Security

VoidAccess is a self-hosted, MIT-licensed dark web OSINT platform that runs a 13-step pipeline from a research query to a relationship graph. It collects from Tor indexes, paste sites, code forges, security feeds and .onion seeds, applies content-safety filters, and exports STIX 2.1, MISP, Sigma, YARA, Snort, Suricata, CSV and JSON. It runs as a CLI with SQLite or as a Docker Compose stack with PostgreSQL, FastAPI and Next.js.

github.comrepoAdded 21 Oct 2026, published 20 Oct 2026🛡️ Security

OWASP MCP Security Testing Guide is a living, GPL-3.0 collection treating the Model Context Protocol as a security boundary from user through model, MCP client, MCP server and tool to the target system. It covers threats, secure development, host/client controls, supply chain, enterprise gateways, detection, incident response, taxonomy, public incidents, case studies and review checklists, with 79 tests in Chapter 3 (sections 3.1–3.19). It includes a finding template, and it links the MCP Goat lab for safe practice. It is useful to AppSec, red team and SOC people assessing MCP deployments.

github.comrepoAdded 17 Oct 2026🛡️ Security

Aikido Safe Chain is an open-source local proxy and shell-alias wrapper for npm, yarn, pnpm, bun, pip, uv, poetry, pipx and pdm. It checks every package download, including deep dependencies, against the Aikido Intel malware feed and blocks malicious packages before install. It also enforces a configurable 48-hour minimum package age by suppressing too-new versions in registry metadata. It supports custom registries and a self-hosted malware-list mirror, and has CI/CD install recipes for GitHub Actions, Azure Pipelines, CircleCI, Jenkins, Bitbucket and GitLab.

github.comrepoAdded 17 Oct 2026🛡️ Security

Model card for Meta Superintelligence Labs' Muse Spark Open, an open-weights, natively multimodal model with 816B total and 42B active parameters and a 1M-token context window. It targets coding and agentic work (tool use, long-horizon tasks, multimodal reasoning, synthetic data generation, LLM-as-judge). It ships in BF16 and NVFP4, needs about 700GB VRAM (NVFP4) or 2TB (BF16), runs on SGLang, vLLM, Transformers, TensorRT-LLM, Unsloth, llama.cpp and MLX, and supports a reasoning_effort setting. The Muse Model License requires "Built with Muse Spark Open" attribution and a separate agreement for Model-as-a-Service above $20M revenue. The card reports safety results against Kimi K3 on cyber, chem/bio and loss-of-control evals.

huggingface.corepoAdded 17 Oct 2026🧠 AI

PS5LM is a homebrew app for jailbroken PS5s (firmware 7.00–13.60). It runs llama.cpp with the ggml-vulkan backend on the console's RDNA 2 GPU, using 11.4 GB of shared memory, and loads any GGUF model. It serves OpenAI /v1/chat/completions, Anthropic /v1/messages (usable from Claude Code, Codex and opencode) and a browser chat page on port 8081. It also supports image-projector vision models and TypeSafe-style decision models through a /v1/systemone endpoint. A planner picks the longest context and best cache that fit the free memory, and the app downloads models from Hugging Face.

github.comrepoAdded 17 Oct 2026, published 16 Oct 2026🧠 AI

Release notes for python-1.20.0 of Microsoft's Agent Framework, an open-source agent/workflow orchestration library. This release adds native vector-store connectors for DuckDB, SQL Server and MongoDB plus a TypeSafe AI connector, redesigns Foundry hosting around request-scoped agent factories and sandbox-isolated sessions, adds computer-use support to Responses clients, and ships Magentic manager and handoff-routing improvements for multi-agent orchestrations alongside a large batch of MCP, Bedrock, Gemini, Anthropic and Ollama provider fixes.

github.comrepoAdded 6 Oct 2026🧠 AI

jev-ultrafast is an open-source browser automation agent (from Browser Use) that represents each page as an indexed element table and uses a 'TypeSafe' policy to speculatively predict both the next operation (CLICK, TYPE_TEXT, SELECT, SCROLL, WAIT, DONE, BLOCKED) and its target in a single network round trip, only invoking a small LLM (e.g. inception/mercury-2.5 via OpenRouter) to generate text when the operation is TYPE_TEXT. The repo includes a local inspector UI, Chrome automation via a 'Browser Harness' tool, offline tests, and published before/after benchmarks showing a Google Flights search dropping from a median 9.45s to 7.09s and browser protocol calls from 1,092 to 101 across repeated runs.

github.comrepoAdded 6 Oct 2026🧠 AI

OKX Agent Trade Kit is an open-source MCP server (okx-trade-mcp) and CLI (okx-trade-cli) that let AI assistants like Claude Desktop, Cursor, Claude Code and VS Code place trades and query account data on the OKX exchange via natural-language commands. It runs locally with API keys never leaving the machine, supports module scoping (market, spot, swap, account, earn), a read-only mode for safe querying, multiple profiles, and includes pre-built skill files for agent frameworks plus structured JSON error reporting for debugging failed tool calls.

github.comrepoAdded 2 Oct 2026🧠 AI

ldraw-nova is an open-source agentic pipeline where an LLM agent (tested with models like Claude Opus 5.5 and GPT-6 Astra) takes a build prompt, reads LDraw-building instructions, and produces a plan.json describing a model's geometry. From that plan it writes a Python generator script that, when executed, outputs an LDraw (.mpd) 3D CAD source file, viewable in 3D/VR (Meta Quest 3) or exportable to Blender-editable glTF. The agent uses jev-rerank, a semantic search tool with reranking backed by TypeSafe's Jev System One model, to find suitable LEGO parts and example models, falling back to full-text search without an API key; it also uses headless rendering and collision/gap detection to self-inspect and iterate on designs.

github.comrepoAdded 3 Oct 2026, published 2 Oct 2026🧠 AI

OpenShell is NVIDIA's open-source runtime for safely running fleets of autonomous AI agents: each agent runs in an isolated sandbox where kernel-level controls enforce a declared policy over file access, syscalls, and network connections, and credentials are injected only for approved endpoints rather than exposed to the agent directly. Policy changes are checked with formal verification to flag risky new access (new hosts, new API methods) before they're approved, and the project ships a CLI, gateway, Kubernetes/Helm deployment, and a tutorial running OpenCode against an OpenRouter model.

github.comrepoAdded 1 Oct 2026🛡️ Security

OpenShell is NVIDIA's open-source runtime for running fleets of autonomous AI agents inside isolated sandboxes. Declarative policies cover filesystem, syscall, process and network access. These are enforced at the kernel level, and credentials are injected only into requests bound for approved endpoints. Policy changes are checked with formal verification so risky new access waits for human review. It ships a CLI, a gateway control plane (Helm deployment on Kubernetes), SDKs, extensibility hooks (middleware, interceptors, compute drivers) and installable agent skills, and it can run agents such as OpenCode.

github.comrepoAdded 1 Oct 2026🧠 AI

Jevgrep (the `jg` CLI) lets a coding agent ask a natural-language question about a repository and get back relevant files, reading leads, and verbatim source excerpts in one response, using an LLM (Jev) to judge relevance across folders, files, and declarations instead of relying on grep/ripgrep alone. It ships an installable "skill" for Claude Code, Codex, OpenCode and other agents that teaches them when to call jg versus their normal tools, and requires a key for Vercel AI Gateway, TypeSafe, OpenRouter, or OpenCode Zen. A reported ten-task SWE-bench repeat found ~40% lower coding-agent cost ($7.62 to $4.52) but a lower solve rate (7/10 vs 8/10 baseline), explicitly framed as a cost/quality tradeoff rather than a win.

github.comrepoAdded 27 Sep 2026, published 26 Sep 2026🧠 AI

who-let-the-agents-act is a self-hostable lab suite (Docker/Python, Groq-backed LLM agent) with nine isolated scenarios — overpowered data tools, IDOR-style cross-account access, unsafe agent handoffs, refund-limit bypass, indirect prompt injection via poisoned invoices, multi-tenant RAG leakage, secret leakage through debugging, fail-open approval outages, and a multi-hop confused-deputy agent chain. Each scenario runs in multiple modes (vulnerable vs. application-enforced) against the same prompt, recording model plan, policy decision, tool calls, and DB access as JSON so a reader can directly compare what changes when authorization is enforced outside the system prompt.

github.comrepoAdded 26 Sep 2026🛡️ Security

shai-hulud-detect is a dependency-free Bash scanner that checks projects against a 5,782-entry list of compromised npm, PyPI, Composer, Crates, Go, Hex, and RubyGems package versions, plus content-pattern indicators of compromise (malicious file hashes, C2 domains, dead-man's-switch artifacts, forged commits, suspicious lifecycle hooks) tied to the Shai-Hulud supply-chain attack waves. It supports single-project and bulk scanning, CI-friendly exit codes, JSON/log output for pipeline gating, and a --check-host mode to detect the May 2026 gh-token-monitor/kitty-monitor persistence daemons that wipe hosts if their monitored GitHub token is revoked (with a documented safe remediation order). Detection is read-only; new package entries are sourced from named threat-research firms (Socket, StepSecurity, Aikido, Snyk, JFrog, Wiz, Semgrep, SafeDep, GitGuardian, OX Security) and cited in PRs.

github.comrepoAdded 23 Sep 2026🛡️ Security

A Chinese translation (with original source notes) of a design essay synthesizing TypeSafe founder Diogo Almeida's notes on 'Jev,' a typed decision model that drives a coding-agent harness. It argues coding agents are simple loops whose real leverage lies in how context is assembled each turn, and works through six problems inherited from KV-cache-driven, append-only context design: costly model routing, tool-schema bloat, lossy compaction, rare sub-agents, destructive session restarts, and the built-in-capabilities tradeoff. It proposes fixes including query-aware context scoring/visibility tiers, cost-aware routing that accounts for cache reprocessing, tiered tool disclosure, conditional AGENTS.md loading, and shared read-only background retrieval.

github.comrepoAdded 26 Sep 2026, published 22 Sep 2026🧠 AI

Shor is a source-available, multi-tenant autonomous pentesting platform where a ~17-agent LLM pipeline (discovery, hypothesis, adversarial screening jury, exploitation, proof replay) attacks a target URL and optionally its connected source repo. It wields 30+ real offensive tools (sqlmap, dalfox, nuclei, jwt_tool, hydra, ffuf, etc.) plus SAST/secret/SCA tools (Semgrep, Gitleaks, TruffleHog, OSV-Scanner, Trivy) in white-box mode, and only reports findings whose PoC is deterministically re-executed and confirmed by a code-enforced safety layer under a signed Rules of Engagement, with scan authorization gated behind single-use human-minted tokens on its MCP/automation surface.

github.comrepoAdded 22 Sep 2026, published 19 Sep 2026🛡️ Security

hermes-jev-skills wires TypeSafe's small, fast decision model "Jev" into agent workflows (Hermes, Claude Code, Codex) to handle cheap sub-decisions — which model should answer a turn, which of many skills to load, which retrieved passages matter, which conversation turns survive a summary — instead of burning frontier-model tokens on them. It ships ten agent-agnostic SKILL.md files, a CLI (jev routing/mail/screen/search), a local dashboard, and a plugin built on public Hermes seams (pre_llm_call, transform_tool_result, llm_request middleware) with detailed data-redaction guarantees for what gets sent to the Jev API. It also includes a shadow mode for safely evaluating routing decisions before enabling them.

github.comrepoAdded 26 Sep 2026, published 18 Sep 2026🧠 AI

jev-gateway is a local proxy that sits between coding agents (Codex, Claude Code, OpenCode, Kilo, Gemini CLI, Devin) and their LLM backend, intercepting only the tool-selection decision and routing it to TypeSafe's small, fast "Jev" model instead of the main reasoning model, while forwarding everything else untouched. It supports forced tool_choice, hint-based suggestions (for APIs like Anthropic's that can't force a tool mid-turn), a live dashboard for cost/latency/routing metrics, and a companion benchmark repo (jev-gateway-bench) showing routing helps most on debugging tasks but can hurt some models on feature-building tasks.

github.comrepoAdded 26 Sep 2026, published 18 Sep 2026🧠 AI

Abide is a CLI (npx @coldtea/abide) that hooks into Claude Code, Codex and OpenCode to check every agent edit or turn against project rules written in AGENTS.md/CLAUDE.md that a linter can't enforce (e.g. 'never let a raw error reach a user', 'no premature abstractions'). It uses Jev, TypeSafe's calibrated decision model, to answer a typed yes/no probability per rule per diff instead of a full LLM call, making it cheap (~300ms, fractions of a cent per turn) enough to check every edit; violations above a threshold are fed back to the agent to repair in the same turn.

github.comrepoAdded 26 Sep 2026, published 18 Sep 2026🧠 AI

An extensive, actively maintained GitHub "awesome list" cataloging the ecosystem that has grown around TypeSafe's Jev and its "System One" typed decision models — a non-generative alternative to chat LLMs that returns calibrated probabilities per option (Choice/Score/Noul primitives) via RLCD training and single-pass constrained decoding. It indexes dozens of open-weight reproductions (OneJev, Rizzo Flow, Laya, Jebadiah, kev), benchmarks and leaderboards (JevBench, Jev Decision Index, JevAdvBench, DecisionBench), downstream tools (browser/robot/trading agents built on the typed API), and the research lineage the design draws on (zero-shot entailment classifiers, InstructGPT's reward model, GLiNER/GLiClass, monoBERT, LLaDA, vLLM, DSPy, RouteLLM, Constitutional Classifiers). It also links commentary auditing TypeSafe's claims (accuracy vs. frontier LLM baselines, security issues found in community tools).

github.comrepoAdded 29 Sep 2026, published 17 Sep 2026🧠 AI

A community-maintained GitHub list cataloging "decision models" (also called System One models): small/fast models that take a state plus caller-declared questions (Noul/true-false, Choice/multi-option, Score/rubric) and return a probability per answer in one forward pass, rather than generating text. It tracks the originating TypeSafe AI Jev model and its /v1/systemone API alongside competing hosted models (Upstage Solar Decide, Liquid AI's d1, OpenAI's Decisions API, Inception's Mercury Decide, Respan's Span-01), dozens of open-weight fine-tunes (Cloudflare's Clef, Perplexity's pplx-decider, AWS Strands Decider, Together AI's Tev1, and many Qwen3.5-based community models), zero-training logit-reading approaches, local runtimes (Ollama, Ollaya, llama.cpp-based servers), SDKs across a dozen languages, and a very long list of agent/coding-tool/MCP integrations (browser agents, code review, routing, game-playing demos) that use these models for fast, typed, in-the-loop decisions. The page is truncated at 40k of ~51k characters, so later sections (further toys, demos, and possibly benchmarks) are not reflected here.

github.comrepoAdded 2 Oct 2026, published 17 Sep 2026🧠 AI

SkillRanker (sr) is a standalone Rust CLI that ranks which skill an agent should load next, combining local context/roster signals with TypeSafe.ai's Jev model for evaluation and FrankenSearch's Quill BM25 engine for local candidate prefiltering when a skill library exceeds 254 entries. It integrates with Claude Code and Codex via hooks, offers dry-run/explain/replay/eval workflows for inspecting and reproducing ranking decisions, and is explicitly advisory only — it never executes skills or overrides agent instructions.

github.comrepoAdded 26 Sep 2026, published 17 Sep 2026🧠 AI

Decider is an open reproduction of TypeSafe AI's System One (Jev) model class: instead of generating text, it reads a state plus a set of typed questions (Choice, Score, or Noul/yes-probability) and returns a calibrated probability distribution for each in one forward pass, with no decoding or parsing. The repo ships 2B/4B/12B and a 35B mixture-of-experts checkpoint (built on Qwen3.5 and Gemma-4 base models), trained on roughly 95 public datasets plus teacher-labelled data, with per-type temperature calibration, GGUF/llama.cpp and vLLM serving paths, an MPS/Apple Silicon port, and a community Snapdragon X Elite NPU port. It benchmarks against TypeSafe's Jev on JevBench and the Decision Index, documenting where it closes the gap (language, tools, retrieval) and where it lags (knowledge-heavy MMLU/GSM8K/GPQA tasks and calibration on hard items).

github.comrepoAdded 2 Oct 2026, published 16 Sep 2026🧠 AI

pi-jev is an npm extension (@y0usaf/pi-jev) that adds a typed decision layer to the Pi coding agent: a gate scores pending bash/write/edit tool calls on destructiveness, exfiltration risk, scope, and impact before they run, while an output judge scans bash results for leaked secrets and classifies command failures (retry/environment/code_bug/permission/user_error). Answers come back as probabilities or choice distributions rather than prose, are batched into one API round trip to api.typesafe.ai, cached per input, and fail open on any error so a dead endpoint never blocks the agent. The README documents calibration work behind the thresholds (e.g. destructive=0.90, leak=0.90) derived from repeated fixture runs, and details argument/output truncation and key redaction to limit what leaves the machine.

github.comrepoAdded 26 Sep 2026, published 16 Sep 2026🛡️ Security

pi-jev is a decision-layer extension for the Pi coding agent that asks a separate model (Jev/TypeSafe) typed yes/no, choice, or score questions about pending tool calls and their outputs, returning probabilities and confidence scores instead of prose. It gates bash/write/edit calls for destructive, exfiltration, and out-of-scope risk, judges bash output for leaked secrets and failure classification, and exposes a jev_ask tool for the model to request the same structured judgements itself. The README documents empirically calibrated thresholds (e.g. destructive=0.90, leak=0.90) derived from repeated test runs rather than arbitrary defaults.

github.comrepoAdded 26 Sep 2026, published 16 Sep 2026🧠 AI

security-audit-skill is a Cloudflare open-source coding-agent skill that turns an AI coding agent into a structured vulnerability hunter, running six phases: reconnaissance into architecture.md/coverage-ledger.json, coverage-led hunting by isolated sub-agent "hunters," adversarial candidate validation, structured findings.json output validated against a report-schema.json, independent re-verification of claims, and target-neutral report generation (REPORT.md, FINDINGS-DETAIL.md, NEEDS-VALIDATION.md). It is installed via the Skills CLI (`npx skills add`), uses Node.js validators (validate-coverage-ledger.cjs, validate-findings.cjs), requires a sandboxed environment for safely executing target code/tests/fuzzers, and is the single-repo seed for Cloudflare's larger fleet-wide vulnerability discovery harness described in a companion blog post.

github.comrepoAdded 22 Sep 2026, published 15 Sep 2026🛡️ Security

AWSHound is a Go CLI/container tool that collects AWS IAM and authorization data across profiles, config-file opt-ins, or an entire AWS Organization (via cross-account role assumption), and outputs a BloodHound OpenGraph for attack-path analysis. It supports phased collection with on-disk artifacts, offline graph building from previously collected data, and safeguards like --max-api-requests and --max-api-requests-per-minute to bound AWS API traffic during collection.

github.comrepoAdded 8 Sep 2026🛡️ Security

vet is an open-source CLI (from SafeDep) that scans package manifests, SBOMs, container images, and source repos across npm, PyPI, Maven, Go, RubyGems, Cargo, and Packagist to surface vulnerabilities, malicious packages, and license/quality issues. It cuts through CVE noise by analyzing actual code-usage evidence, queries SafeDep Cloud's threat-intelligence database for real-time malware detection (e.g. flagged packages like express-cookie-parser, eslint-config-airbnb-compat), and lets teams enforce security/license/OpenSSF-Scorecard policies as CEL expressions in CI/CD via SARIF/JSON/Markdown reporting.

github.comrepoPublished and added 7 Sep 2026🛡️ Security

A GitHub-hosted book focused entirely on securing the React Native developer's workstation and toolchain rather than the shipped app — covering the polyglot execution surface triggered by a single git clone/yarn/pod install (Ruby, CocoaPods, Xcode build phases/XCSSET, Gradle, gradle-wrapper.jar, keystores), CVE-2025-11953 (exposed Metro/RN dev server), ClickFix-style social engineering of developers, CI-as-extended-workstation risks, and Expo/EAS-specific supply-chain concerns. It ships alongside a separate companion repo of 119 Opengrep detection rules, each mapped to a specific chapter's attack technique, plus practical appendices like a safe-clone runbook and a file risk atlas for hardening teams.

github.comrepoPublished and added 5 Sep 2026🛡️ Security

Open-source (Apache-2.0) AI trading terminal for Hyperliquid where a user sketches a chart read (trendlines, levels, fib retracements) and an agent turns it into a ranked trade setup with entry, stop and target, then generates a Freqtrade Python strategy to trade it. The generated strategy passes through a validator that catches unsafe patterns and sends failures back to the model in a repair loop until the code is safe to deploy, a pattern documented in docs/strategy-pipeline.md. It is self-hostable or available as a hosted build, and also exposes an agent-facing entry point (SKILL.md) for coding agents like Claude Code, Codex and Cursor to trade directly without the UI.

github.comrepoAdded 2 Oct 2026, published 21 Aug 2026🧠 AI

ITScape is a guest-to-host escape exploit (CVE-2026-46316) against KVM/arm64, discovered by Hyunwoo Kim (@v4bel), exploiting a race condition in the vGIC-ITS (Interrupt Translation Service) emulation inside the Linux kernel's in-kernel KVM code rather than QEMU userspace. A malicious guest with only EL1 (guest kernel) privilege can trigger the bug via GIC/ITS MMIO to gain host kernel (root) code execution, threatening isolation on multi-tenant arm64 public clouds; the repo includes a reproducible PoC built on the Linux kvm selftest framework and QEMU TCG for safe testing, plus patch/version range and disclosure timeline.

github.comrepoPublished and added 15 Aug 2026🛡️ Security

SiberKapan is a Turkey-focused, community-driven open-source threat intelligence platform that aggregates data from FortiGate webhooks, an 11-service honeypot (HoneypotKapan), nginx/Fail2ban log watchers, and external feeds, publishing it as STIX 2.1/TAXII 2.1, a MISP default feed, Sigma/Suricata/Wazuh exports, and REST blocklists. It also runs a real-time phishing/domain-squatting detector via Certificate Transparency log monitoring with fuzzy typosquat and Punycode/IDN decoding, and safely fingerprints SSH-honeypot malware downloads with SSRF-protected, never-executed hashing enriched via MalwareBazaar. The write-up details concrete anti-abuse safeguards: time-based IP score decay, CDN/cloud-proxy allowlisting, UDP-spoofing exclusion, RFC1918 rejection, and manual review gating for weak phishing signals.

github.comrepoPublished and added 8 Aug 2026🛡️ Security

autoguardrails is an open-source alignment research scaffold from Santander AI Lab, inspired by Karpathy's autoresearch pattern, that searches over a single mutable policy.md file to minimize attack success rate (ASR) against a fixed jailbreak/obfuscation eval suite while enforcing a benign-pass floor so the guardrail can't just refuse everything. It reports asr_unguarded, asr_with_policy, and policy_delta to isolate the guardrail's contribution from the target model's native safety, and supports both an offline deterministic stub and real OpenAI-compatible target/judge models.

github.comrepoPublished and added 5 Aug 2026🛡️ Security

SecureAI-Scan is an offline CLI that performs import-resolved dataflow analysis on TypeScript, JavaScript, and Python code to find LLM/MCP/Agent-Skill/RAG-specific risks (prompt injection, tool poisoning, unsafe output handling, vector-store access control), mapped to the OWASP Top 10 for LLM Applications, Agentic Applications, and MCP Top 10. It distinguishes proven dataflow traces from heuristic keyword matches, scans .mcp.json/claude_desktop_config.json/SKILL.md for tool-poisoning and command-injection patterns (citing the WhatsApp MCP rug-pull and postmark-mcp backdoor), and includes evasion-resistant deobfuscation checks built in response to the "Cloak and Detonate" adversarial study (arXiv:2607.02357) that bypassed most published skill scanners. It also runs offline advisory checks against known-malicious/vulnerable packages (validated against CVE-2025-6514 and CVE-2024-34359) and integrates via GitHub Actions, pre-commit hooks, SARIF output, and an MCP server for Claude Code.

github.comrepoPublished and added 5 Aug 2026🛡️ Security

open·kritt is a self-hosted, open-source platform that orchestrates AI coding agents (Codex, Claude Code, or Grok Build) in parallel to hunt for vulnerabilities in remote or local repositories and their dependencies. It breaks security research into small chained prompt "workflows," runs jobs in disposable root-access Docker containers with internet access, then de-duplicates and ranks findings, validates them via post-scripts/PoC generation, and exports share-safe finding bundles. It's the open-source distillation of the internal tooling behind the Kritt team's (Blockian) $1.5M+ in bug-bounty payouts.

github.comrepoPublished and added 2 Aug 2026🛡️ Security

GenOffice is an open-source (Apache-2.0) desktop office suite for macOS/Windows/Linux that opens native .docx/.xlsx/.pptx/PDF/Markdown/HTML files and puts an AI agent inside the editor, applying edits as byte-preserving diffs, tracked changes and live spreadsheet formulas rather than pasted text. It exposes the same engines to coding agents via a `genoffice` CLI, a bundled skill for Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode and Windsurf, and an MCP server with 29 tools (plus an HTTP variant for headless/remote use), and includes a local SQLite full-text file search optionally reranked by TypeSafe's Jev judgment model. Users can bring their own key (Claude, OpenAI, Gemini, DeepSeek, and others) or sign in with Genspark to route model calls through a proxy.

github.comrepoAdded 30 Sep 2026, published 31 Jul 2026🧠 AI

hackingtool is a console launcher that bundles 215 curated security tools across 21 categories (recon, OSINT, wireless, phishing, forensics, post-exploitation) so users can install and run them without hunting down individual Git repos. Its newer AI layer maps plain-English goals to the right tool and exact command, plans multi-step objectives with confirmation gates, and drafts engagement reports, while emphasizing safe installs (pinned/SHA-256-verified downloads, no curl|bash, list-form subprocess calls, signed releases with SBOM) and refusing out-of-scope asks like DoS or mass-targeting. It also ships a non-interactive orchestrator (`--engagement`/`--pipeline`) that normalizes tool output into findings.json for red team, blue team, OSINT, bug bounty, and DFIR workflows.

github.comrepoAdded 3 Sep 2026, published 31 Jul 2026🛡️ Security

A "battle-tested" collection of Semgrep rules by researcher 0xdea aimed at C (and some C++) vulnerability hunting, covering buffer overflows, use-after-free/double-free, format string bugs, integer truncation/wraparound, command injection, insecure APIs (gets, strcpy, sprintf, scanf family), privilege management ordering, ReDoS, and dozens of other memory-safety and secure-coding checks. Rules are published to the Semgrep registry as "p/0xdea" and can be run directly via `semgrep --config "p/0xdea"` or cloned locally, with SARIF output support for triage in VS Code via SARIF Explorer. The repo also documents a roadmap including porting rules to the Semgrep Pro engine for taint/inter-procedural analysis.

github.comrepoAdded 3 Sep 2026, published 31 Jul 2026🛡️ Security

whatisit is a CLI that turns plain-English requests into shell commands using a 941 MB Q4_K_M GGUF model (LoRA fine-tune of Qwen2.5-Coder-1.5B-Instruct) served locally via llama.cpp on CPU. It can optionally use any OpenAI-compatible endpoint. It includes a denylist safety checker (DANGER/CAUTION) with 477 regression cases. On the 300-task InterCode-ALFA benchmark (NL2SH, NAACL 2025) the fine-tune scores 0.620 vs 0.540 for the base (McNemar p=0.004), roughly equal to the untuned 7B and about 11 points behind GPT-4o. A 3B variant is also available, and the author documents the training recipe, data mix and limits.

github.comrepoAdded 16 Oct 2026, published 29 Jul 2026🧠 AI

recons101x (shodan_reconsx) is a passive-by-default Python CLI that enumerates hostnames published to certificate transparency logs via ctl.shodan.io, requiring no Shodan API key. It supports optional active features — DNS resolution, TCP/HTTP reachability probing on ports 443/80, bounded live scans, and certificate metadata enrichment — with status states (DNS_ONLY, TCP_REACHABLE, HTTP_REACHABLE, STALE), JSON/TXT output, and safeguards like --max-time, --active-only, and explicit warnings to only scan authorized domains.

github.comrepoAdded 30 Sep 2026, published 29 Jul 2026🛡️ Security

Bug Bounty Lab101 is a workspace that structures the real HackerOne bug bounty workflow: document program scope, run scope-gated recon/vuln scanning via bugbounty-hunter.sh (backed by a 400+ tool arsenal spanning recon, DNS enumeration, web scanning, exploitation, and cloud/subdomain-takeover checks), then produce a triage-ready H1 report with Hacktivity dedup checks. It also integrates T3MP3ST, a separate multi-agent offensive framework that connects local AI coding agents (Claude Code, Codex) to automate target investigation, and ships a legacy-vm-practice lab (DVWA/Metasploitable-style) for safe skill-building outside real program scope.

github.comrepoPublished and added 25 Jul 2026🛡️ Security

SeClaw is a benchmark framework for evaluating security risks of autonomous LLM agents, combining spec-driven synthesis of security tasks (covering resource, task, environment, and intrinsic-agent risk categories) with execution-based evaluation in a Docker sandbox. The repo ships SeClaw-Bench, a public dataset of 150 OpenClaw task directories, plus batch-execution scripts that record full agent trajectories (tool calls, file ops, outputs) and grade them against a multi-dimensional risk rubric covering information leakage, privilege misuse, content safety, and compliance risks, rather than only judging final responses.

github.comrepoPublished and added 22 Jul 2026🛡️ Security

A dual-track research lab reconstructing Fastjson RCE chains: a legacy JDK 8 direct-remote-class JSONType RCE for Fastjson 1.2.83, and a modern JDK 17 retained-JAR via proc-self-fd composition that works even with AutoType disabled and DTO binding in place, exploiting how ParserConfig.checkAutoType probes every type value via getResourceAsStream. It also reproduces an independent fastjson2 2.0.57/2.0.62 autoType bypass disclosed by Chaitin, where ObjectReaderSeeAlso hardcodes SupportAutoType, letting seeAlso/JsonSubTypes/sealed-type modeling trigger remote class loading even with autoType disabled. The repo ships dependency-free Python scanner tools for passive log detection, static artifact inventory, and safe active reachability probing via Burp Collaborator or interactsh.

github.comrepoAdded 2 Oct 2026, published 20 Jul 2026🛡️ Security

SingGuard-NSFA is an open-source guardrail framework (released as 0.8B/2B/4B/9B model checkpoints) that targets operational threats in LLM agents—prompt injection, sensitive-info extraction, malicious code requests, tool misuse, and resource exhaustion—rather than just content-safety issues. It's built on a CIA-triad-grounded taxonomy of 185 risk variants across 7 domains (cross-validated against OWASP guidelines) and a 133-language benchmark with 93K+ samples, offering both generative chain-of-thought auditing and ~50ms real-time classification heads. It beats Llama Guard 3, WildGuard, and GPT-5.1 by 6-12 F1 points on multilingual benchmarks, and can also be plugged into Llama Guard 3 as a lightweight enhancement (+17.6 F1).

github.comrepoPublished and added 19 Jul 2026🛡️ Security

LLM Guard (Protect AI) is an open source Python toolkit that wraps input/output scanners around LLM applications to detect and block prompt injection, PII/data leakage, toxic or harmful content, and other unsafe interactions, with a pip-installable library and API deployment option. The project has since been archived and is no longer maintained, though the code and associated Hugging Face models remain publicly available.

github.comrepoAdded 3 Sep 2026, published 14 Jul 2026🛡️ Security

Giskard is an open-source Python testing/evaluation library for agentic and LLM systems, rewritten in v3 as a modular set of packages (giskard-checks, giskard-scan, giskard-core, giskard-llm, giskard-agents). giskard-scan is the red-teaming layer: it auto-generates adversarial test suites from a plain-language agent description, covering prompt injection, harmful content, stereotypes, and misinformation across OWASP LLM Top-10 categories, and includes a built-in prompt-injection payload dataset. giskard-checks provides LLM-as-judge and assertion-based evals (Groundedness, Conformity) for catching regressions and enforcing safety rules in multi-turn agent conversations; the legacy v2 also offered a tabular ML bias/robustness scanner and RAGET for RAG test-set generation.

github.comrepoPublished and added 14 Jul 2026🛡️ Security

NeMo Guardrails is NVIDIAs open-source Python toolkit (nemoguardrails) for adding programmable rails between an application and an LLM, covering input, dialog, retrieval, execution, and output stages. It ships built-in defenses against jailbreaks and prompt injection, self-check fact-checking and hallucination detection, sensitive-data masking, integrations with NVIDIA safety models, ActiveFence and PolicyAI moderation, LangChain, and a Colang DSL for defining conversational flow rails, plus a CLI/server and an evaluation tool for vulnerability scanning against sample bots.

github.comrepoPublished and added 14 Jul 2026🛡️ Security

Purple Llama is Meta's umbrella repo of tools and evals for building safely with generative AI, bundling Llama Guard (input/output content moderation fine-tuned on Llama 3.1/3.2), Prompt Guard (detects prompt injection and jailbreak attempts), Code Shield (inference-time filtering of insecure LLM-generated code and code-interpreter abuse prevention), and the CyberSec Eval benchmark suite (CWE/MITRE ATT&CK-based tests now spanning insecure code generation, offensive cyber capability, spear-phishing, and visual prompt injection). It matters as one of the first industry-wide, MIT-licensed benchmark and safeguard sets specifically for LLM cybersecurity risk.

github.comrepoPublished and added 14 Jul 2026🛡️ Security

api-relay-audit is a zero-dependency, locally-run Python security audit tool for AI API relays and LLM proxies that sit between a user and providers like Anthropic or OpenAI. It runs a 14-step check covering hidden prompt injection/extraction, context truncation, model-identity substitution, tool-call/package-command tampering, and SSE stream integrity, producing a reviewable Markdown report with LOW/MEDIUM/HIGH findings (inconclusive results stay visible rather than being marked clean). It also adds a web3 profile for wallet-safety probes (transfer guidance, signed-transaction refusal, private-key refusal) and is distributed as a standalone script, a DeepSeek Harness (DSH) plugin, and OpenClaw/Hermes agent skills.

github.comrepoPublished and added 4 Jul 2026🛡️ Security

RAMPART (Risk Assessment & Measurement Platform for Agentic Red Teaming) is a Microsoft-built pytest-native framework for writing and running safety and security tests against agentic AI applications. It structures tests around adversarial attacks, benign failure modes, and harm categories, using evaluation-driven assertions integrated directly into pytest workflows.

github.comrepoPublished and added 4 Jul 2026🛡️ Security

Pentest Swarm AI is an open-source (AGPL-3.0), self-hosted CLI tool that runs dozens of LLM agents concurrently against a target, coordinating through a shared "stigmergic" blackboard rather than a fixed recon→exploit→report pipeline, so findings propagate and wake relevant agents in real time. It supports any provider with tool-calling (Claude, OpenAI-compatible endpoints, Together AI-hosted Llama/Qwen/DeepSeek/GLM, or fully local Ollama/LM Studio), ships bundled vulnerable labs (crAPI, Juice Shop, VAmPI, DVGA) for safe testing, and positions itself against the closed SaaS bug-bounty bot XBOW. It currently automates verified attack playbooks (BOLA/IDOR, mass assignment, NoSQL injection) with evidence-backed reporting, with roadmap items for runtime object-reference mining, self-correcting attacks, and on-demand specialist sub-agents.

github.comrepoPublished and added 21 Jun 2026🛡️ Security

SkillSpector is NVIDIA's open-source scanner for AI agent skills (used by Claude Code, Codex CLI, Gemini CLI, etc.), detecting 71 vulnerability patterns across 17 categories including prompt injection, data exfiltration, privilege escalation, MCP tool poisoning, and supply-chain issues via static analysis, AST checks, YARA rules, and optional LLM semantic evaluation. It cites research showing 26.1% of a 31,132-skill sample contain vulnerabilities and 5.2% show likely malicious intent, and can run as a CLI, MCP server, or install gate producing JSON/SARIF risk scores and DO_NOT_INSTALL/CAUTION/SAFE recommendations.

github.comrepoPublished and added 14 Jun 2026🛡️ Security

offensive-claude is a Claude Code plugin/framework that structures pentest engagements around the Cyber Kill Chain, providing 32 kill-chain skills, 8 collaborative agents, a SessionStart discipline dispatcher, and a 47-file vulnerability pattern reference library (injection, memory safety, auth, crypto, AD attacks, etc.). It also ships a staged crash-to-exploitability pipeline (rr record/replay root-causing, gcov reachability proof, ASAN/hardened feasibility profiling, Z3-based path-condition solving) invoked via /engage.crash, plus quality-gated phase templates requiring CWE/CVSS/ATT&CK-mapped evidence before findings are marked confirmed.

github.comrepoAdded 3 Sep 2026, published 22 May 2026🛡️ Security

AG Kit is an open-source Antigravity-first agent engineering toolkit that installs a `.agents/` workspace contract of rules, skills, specialist agents, workflows, persistent memory, and MCP configuration for Google's Antigravity coding-agent runtime. It ships a native PreToolUse safety hook that blocks destructive commands (root-filesystem deletion, drive formatting, raw-disk overwrites) without replacing Antigravity's own permissions or sandboxing, plus a CLI (`ag-kit init`/`update`/`rollback`) with merge-aware, backed-up updates and SemVer-versioned, drift-checked toolkit manifests.

github.comrepoAdded 22 Sep 2026, published 15 May 2026🧠 AI

Android-Pentesting-Skill is an open-source "skill" package that turns an AI coding agent (Claude Code, OpenCode, etc.) into an Android APK security auditor. It orchestrates APKTool/JADX decompilation, MASTG-aligned Semgrep static rules, source-to-sink tracing, a Runtime Defense Analysis engine that maps detected RASP/anti-tampering protections (root detection, SSL pinning, Frida detection, SafetyNet, Approov, DexGuard, etc.) to reusable Frida bypass profiles, and CVSS 4.0/MASVS-scored professional reporting, plus smali patching/repackaging workflows for authorized lab use. It ships 37+ bundled Frida scripts, 70+ Semgrep MASTG rules, and framework-specific handling for Flutter, React Native, Cordova, and Unity apps.

github.comrepoPublished and added 7 May 2026🛡️ Security

Agent Governance Toolkit (AGT) is a Microsoft open-source framework that intercepts every tool call, message, and delegation made by an AI agent in deterministic application-layer code before it reaches the model, enforcing YAML/OPA/Cedar policies, agent identity (SPIFFE/DID/mTLS), and tamper-evident audit logs. It ships SDKs for Python, TypeScript, .NET, Rust, and Go, a Claude Code plugin, and CLI tools (agt verify, agt red-team scan) for OWASP-style compliance checks and prompt-injection audits. The project explicitly frames prompt-level safety as insufficient, citing a 100% adversarial attack success rate on GPT-4o/Claude 3/Llama-3 (Andriushchenko et al., ICLR 2025) as motivation for application-layer enforcement instead.

github.comrepoPublished and added 6 May 2026🛡️ Security