45 results for “Harness”

llm-trails is an open study of what LLMs choose to do next inside a breached AWS account. It puts 14 models in 13 post-compromise situations, records only a single-turn plan with nothing executed, and codes each answer to CloudTrail events. The repo has the llmtrials harness, prompts, codebook, processed dataset (viz_data.json) and an interactive dashboard, so the study can be rerun or extended.

github.comrepoAdded 30 Oct 2026🧠 AI

llm-trails is a research repo that placed 14 LLMs in 13 post-compromise AWS situations, asked only for their next move (single-turn, nothing executed), and coded each answer to CloudTrail events. It includes the llmtrials harness, prompts, codebook, processed dataset (viz_data.json) and an interactive dashboard. Rates are conditioned on the situation shown, and the aim is turning model behavior into detection priorities.

github.comrepoAdded 30 Oct 2026🛡️ Security

ECC (affaan-m/ECC) is an open-source performance optimization system for AI coding agents. It packages 261+ skills, 64+ agents and 84+ commands that tune Claude Code, Codex, Cursor and other agent harnesses for speed, memory and security. Practitioners can use it as a ready-made skills and harness configuration set. The RepoDir page gives only this short description, with no install steps or benchmarks.

repodir.comrepoAdded 24 Oct 2026🧠 AI

Model card for DeepSeek-V4.1-Flash-1017, a minor update to DeepSeek-V4.1-Flash with MIT-licensed weights. It claims gains in reasoning, coding, agentic tasks and visual benchmarks, with shorter task time and output length that move the performance–cost Pareto frontier across agent harnesses (Claude Code for Terminal-Bench 4.0, Mini-SWE-V2 for DeepSWE v1.1). It ships no Jinja chat template. It provides a reference encoding.py for multi-turn chat, tool calling, thinking mode, numeric reasoning effort and interleaved images, plus deepseek-recipe, Rust libraries with Python bindings for prompt encoding and output parsing. Serving recipes are given for Transformers, vLLM, SGLang and Docker Model Runner.

huggingface.corepoAdded 18 Oct 2026, published 17 Oct 2026🧠 AI

Companion repository for Omar Santos's Pearson and O'Reilly trainings and books. It has eight parts of runnable Python labs: chat models, embeddings, prompt templates, LCEL prompt chaining, Chroma-based RAG, ReAct/LangGraph/CrewAI/DeepAgents agents, and FastMCP servers (nmap, CISA KEV, Shodan). It also includes guides to six agentic frameworks (OpenClaw, Hermes, Agent Zero, OpenHands, Paperclip, Buzz), a tokenomics module on agent cost (context compounding, prompt caching, model routing, token budget guards, batch API, cost per accepted outcome), and a vendor-neutral design spec for a human-gated multi-agent assessment harness. It is a current, practical curriculum for building and operating agents. Some examples act on real systems and should only be run in an authorized lab.

github.comrepoAdded 13 Oct 2026🧠 AI

Omar Santos's companion repo for his Pearson/O'Reilly trainings and books, organised in eight parts. They cover LangChain prompts, chains and RAG (Chroma), and agents (LangGraph, CrewAI, DeepAgents). They also cover FastMCP security servers (nmap, CISA KEV, Shodan) and attack-surface-management and SOC agent examples. Later parts have security guides to six agentic frameworks (OpenClaw, Hermes, Agent Zero, OpenHands, Paperclip, Buzz) with hardening notes and 2026 CVE mapping, agent cost/tokenomics scripts including denial-of-wallet budget guards, and a vendor-neutral spec for a human-gated multi-agent security-assessment harness (scope manifest, approval gates, kill switch). Useful as a hands-on path into AI-agent security tooling, with warnings that some examples act on real systems.

github.comrepoAdded 13 Oct 2026🛡️ Security

Apogee is a privacy-first browser extension (Chrome/Firefox) that summarizes articles, YouTube/Bilibili videos, PDFs, DOCX and pasted text entirely on-device, inspired by Mozilla's discontinued Orbit. It runs models via WebGPU or WebAssembly in the browser, or connects over loopback to a local Ollama or llama.cpp server, with local passage retrieval for Q&A, grounded sentence highlighting, and Opus-MT translation. It shows a practical no-backend, no-API-key architecture for local LLM apps, with a Node.js extractor test harness for contributors.

github.comrepoPublished and added 9 Oct 2026🧠 AI

nanoMuse is an open-source personal AI agent that runs across phone, desktop, and web, built on an on-device sandbox (OpenMinis with proot/Alpine Linux on mobile) and the DeepSeek Harness on desktop with a Python runtime for tool use. Devices share one account and sync conversations through a relay (self-hostable), while the agent proactively acts, retains memory, and pauses before irreversible actions; it is released GPL-3.0-or-later with documentation on install, self-hosting, connectors, and memory.

github.comrepoPublished and added 7 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

security-harness is an open-source Claude Code plugin (also packaged for Gemini CLI, Codex and opencode) that orchestrates subagents — sh-recon, sh-hunter, sh-chainer, sh-verifier, sh-reporter — through a static-analysis pipeline covering 15 vulnerability classes (IDOR/BOLA, SQLi, XSS, SSRF, injection, auth, deserialization, path traversal, secrets, CSRF, XXE, open redirect, crypto, race conditions, file upload), producing README/JSON/SARIF/HTML/PDF reports with PoCs, CVSS and CWE/OWASP mappings. It also ships sh-pr-review, a per-PR merge-gate skill that posts inline findings and a commit status scoped only to code the PR itself introduced or aggravated, with caching, dedup via fingerprints, and a scheduled GitHub Action that keeps its per-class knowledge bases fresh by having one AI agent draft updates from allowlisted sources (OWASP, PortSwigger Research, CWE/CAPEC, HackerOne) while a separate adversarial reviewer agent fails-closed against prompt injection before auto-merge.

github.comrepoAdded 2 Oct 2026, published 29 Sep 2026🛡️ Security

Agent Threat Rules (ATR) is an open, versioned YAML rule format (ATR-YYYY-NNNNN scheme) for detecting AI-agent runtime threats — prompt injection, tool-poisoning, malicious SKILL.md content, and MCP exchange abuse — evaluated by a reference TypeScript engine (with a Python wrapper) shipped as an npm/pip package, CLI, GitHub Action, and Docker scanner with SARIF output. The project positions itself as "Sigma for agent threats," maps rules to OWASP Agentic/LLM Top 10, MITRE ATLAS, and NIST AI RMF, and publishes an extensive (and unusually self-critical) benchmark suite against corpora like garak, PromptBench, and PromptInject, including documented harness bugs and withdrawn recall figures.

github.comrepoAdded 26 Sep 2026🛡️ Security

VulnHunter is a maintained fork of Capital One's open-source agentic security scanner, reworked to run on any agent harness (Claude Code, Codex, Grok/OpenCode) instead of being Claude-Code-specific. The fork's distinguishing work is engineering, not security findings: portable "skill" prompt files with an explicit environment contract, an installer that fails loudly instead of guessing paths, Docker-based sandboxed exploit validation, and a benchmark harness that ran six full scans of one production Go service across five model/harness stacks, finding that result counts swung from 3 to 42 findings depending on how rigorously exploits were validated. It ships three composable skills (/vulnhunt, /vulnhunter-fix, /vulnhunt-fix-verify), a headless batch-runner (harness/), and a deterministic manifest-writing CLI (vh).

github.comrepoAdded 6 Oct 2026, published 22 Sep 2026🧠 AI

A maintained, harness-portable fork of Capital One's open-source VulnHunter — an agentic AI tool that performs attacker-first forward analysis on source code to find exploitable vulnerabilities, falsify weak findings, and produce evidence-backed PoCs rather than pattern-matched SAST alerts. This fork adds containerized (Docker-based) exploit validation, measured-impact PoCs (rows leaked, amplification factor, etc.), and portability across agent harnesses (Claude Code, Codex, Grok, etc.) via environment-contract prompt files, plus an unattended operator (vulnhunter-run) and batch-scanning/benchmark harness tested against OWASP NodeGoat, Juice Shop, and WebGoat.

github.comrepoAdded 6 Oct 2026, published 22 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

Qwen-Planner-Agent is Alibaba's Tongyi MAI Team framework pairing a trained Planner Model with a stateful Harness to execute mobile tasks end-to-end, coordinating tools, persistent memory, reusable Skills, and sub-agents. It introduces Competence-Adaptive Reward-and-Advantage Engineering (CARE), a hybrid supervised+RL training approach, and reports the 27B model reaching 77.05% Overall on MobilePA-Bench at an estimated $2.41 per 1,000 tasks in output-token cost. This repo hosts the technical report/blog and recorded interactive examples rather than model weights or code.

github.comrepoAdded 26 Sep 2026, published 18 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

Research project on two signed vulnerable Windows drivers, DCRCVDrv.sys (MOCOMSYS) and Alinubx.sys (CnCrypt), abused by the Cruciferra MaaS loader to kill AV/EDR processes. It documents their devices, IOCTLs (0x2205C0, 0x222024) and the termination chain (ObOpenObjectByPointer -> ZwTerminateProcess), and gives annotated disassembly, hash-level sample provenance and blocklist-status snapshots. It includes a Rust lab harness with hash validation and dry-run, plus Sigma, YARA and telemetry guidance. Findings carry evidence labels, and the test matrix is limited to Windows 11 24H2 with HVCI disabled.

github.comrepoAdded 11 Oct 2026, published 14 Sep 2026🛡️ Security

Cortico is an open-source agent harness built around an event stream, designed for autonomous, continuously running agents that handle mixed real-time input across chat platforms, live games, and even physical environments. It provides modular LLM provider components (via an internal Responses protocol), unconstrained context/memory management, an isolated extension system called Cortico World, and a WebUI, with a companion AI-assisted extension creator (Cortina) that lets non-developers build extensions through conversation. A reference use case is cortico-world-vtuber, which drives a Live2D model via VTube Studio with streaming TTS and OBS overlay integration.

github.comrepoAdded 26 Sep 2026, published 13 Sep 2026🧠 AI

py-idp is a Python framework for intelligent document processing with a six-stage pipeline (parse, classify, extract, assess, validate, human review). It supports 23 LLM backends including OpenAI, Anthropic, Ollama, and self-hosted Nanonets-OCR2-3B. It adds Pydantic schema extraction, auto-chunking of oversized documents, an eval harness, and a review-driven policy update for confidence. It is dual-licensed AGPL-3.0 and commercial.

github.comrepoAdded 23 Oct 2026, published 31 Aug 2026🧠 AI

Reef is an open-source infrastructure stack for continual self-improving agents, wiring together agent inference, scored feedback, training/updates, and versioned delivery into one loop. It supports two learning surfaces: fine-tuning model weights via RL training steps (using Slime and SGLang on top of models like Qwen2.5-1.5B-Instruct) or evolving an agent's harness — prompts, rules, and skills — through its built-in "Reefine" recipe, which lets a model propose and install harness changes from plain-language requests. It exposes an OpenAI/Anthropic-compatible inference endpoint plus a reporting endpoint for scoring interactions, and ships a recipe catalog (e.g. the SAO recipe referencing arXiv:2607.07508) for pluggable learning strategies.

github.comrepoAdded 2 Oct 2026, published 31 Aug 2026🧠 AI

dsh-trading is an open-source AI trading terminal built on "DeepSeek Harness" (DSH), a Cordis-based microkernel plugin ecosystem, covering crypto, US equities, China A-shares and Hong Kong stocks. Its notable design is a multi-agent team: a "master" lead agent grounds itself in a holdings ledger and user knowledge base, then decomposes work and delegates to persona-pinned subagents — a trader (trading plans/execution), an instrument-researcher (disclosures/fundamentals), and a risk-reviewer (exposure/stress scenarios) — each dispatching bundled domain "skills" and native tools for quotes, news, order books and backtesting. Every order defaults to dry-run simulation, live execution requires explicit opt-in plus interactive human approval, and headless sessions fail closed, illustrating a concrete human-approval-gated tool-use pattern for agentic systems.

github.comrepoAdded 2 Oct 2026, published 30 Aug 2026🧠 AI

pentest-harness is an open-source, plugin-based AI agent framework aimed at authorized penetration tests, bug bounty research, security labs, and CTFs. It provides a "Pentest Mode" offensive-security operating standard, a full agent toolset (shell, filesystem, web research, subagents, background jobs), and a bring-your-own-key multi-provider LLM engine (OpenAI, Anthropic, DeepSeek, Google, Mistral, Groq, OpenRouter, Azure OpenAI) with durable JSONL/SQLite session persistence and an owner-only credential store for API keys.

github.comrepoPublished and added 27 Aug 2026🛡️ Security

unlazy is an agent skill for Claude Code, Codex CLI and other agent harnesses that enforces "completion discipline": before AI-agent work is reported done, it must satisfy a ledger of runnable gates (GATES.md) whose shell/Node checks are executed and whose output must match a declared EXPECT: string, with digest-bound evidence, approval records, and --reverify to re-run already-"complete" gates. It also provides scoped multi-leaf/branch orchestration with lease-based claiming for parallel agent dispatch, a Claude Code Stop-hook that blocks premature completion, and documentation of the threat model (shell resolution, PATH, approval storage) around executing arbitrary checker commands. The README grounds the design in cited research on LLM laziness, premature truncation, and over/under-thinking (e.g. METR's Time Horizon, SlopCodeBench, OptimalThinkingBench, s1), while being explicit that this research motivates but does not prove the tool's effectiveness.

github.comrepoAdded 2 Oct 2026, published 9 Aug 2026🧠 AI

HarnessRouter is a self-hostable (Docker) infrastructure layer that wraps existing agent harnesses such as Codex and Claude Code behind one OpenAI Responses-compatible API, letting a product run tasks, stream progress, manage files/artifacts, and switch harnesses without writing harness-specific integration code. It implements the Unified Harness Protocol (UHP), a versioned, OpenAI Responses-compatible contract with a reference implementation, schemas, and conformance suite, plus features like per-session workspaces, custom harness configuration with tools/skills/MCP servers, and secret redaction via vault references or header-scoped env vars so long-lived tokens never leak through agent output.

github.comrepoAdded 2 Oct 2026, published 9 Aug 2026🧠 AI

OpenHarness (Autonomous) is an open-source command center for running coding agents such as Claude Code, Codex, Cursor, OpenCode, Devin, Amp and Copilot. A native app and per-machine daemon run each agent in its own tmux pane, with a git worktree per harness. Machines are linked by password, with end-to-end encrypted traffic over direct WebRTC, Cloudflare TURN or a keyless relay. It also supports local models (Ollama, MLX-LM, vLLM, Grid) and a Store of domain-specific harnesses (Blender, CircuitJS, MuJoCo, Godogen, Strudel, RDKit, Typst) defined by a harness.json. An optional open-hardware always-on display device shows agent status.

github.comrepoAdded 16 Oct 2026, published 4 Aug 2026🧠 AI

LongHorizon-Harness (AMAP-ML, package lh-harness) is a Python tool that wraps existing coding/computer-use agents (Claude Code, Codex, OpenCode, DeepSeek Harness) in a durable plan → act → verify → checkpoint/recover loop. It separates Manager, Executor and Auditor roles, accepts only independently verified progress as task state, and restarts rounds from the original goal plus the last verified checkpoint. It supports GUI and terminal workflows via computer-use MCP plugins (codex-computer-use, open-computer-use, clawdcursor), a React/FastAPI web workbench, per-role model and backend selection, and eval suites including Terminal-Bench 2.1; an arXiv paper accompanies it.

github.comrepoAdded 12 Oct 2026, published 4 Aug 2026🧠 AI

Google's official repository of Agent Skills covering Google products and technologies, including Google Cloud. Skills are installed selectively via `npx skills add google/skills`, and the repo also bundles Google product plugins combining Skills with MCP servers for use in agent harnesses.

github.comrepoAdded 22 Sep 2026, published 3 Aug 2026🧠 AI

QM is an MIT-licensed, self-hosted "multiplayer" agent harness that lets a company deploy a shared coding/ops agent across Slack and a web app, with per-person and per-room isolated sandboxes, memory, keychains, permissions, and crons. Its security model centers on an org-wide posture (Strict pauses every tool call for approval; Auto blocks private-network access and applies optional content screening; Dangerous disables both) layered under a predeclared command policy that hard-denies things like recursive deletes, plus an explicit Isolated/Open sharing posture that governs cross-scope memory and file access with provenance labeling and audit trails. It supports pluggable harnesses (Pi, OpenCode, Codex, Claude Code) behind a common core and documents its threat model and operator assumptions in SECURITY.md.

github.comrepoAdded 3 Sep 2026, published 1 Aug 2026🛡️ Security

VVAH is Visa's open-source agentic harness that runs an eleven-stage (S0–S11) LLM pipeline to discover, verify, report, and optionally remediate/validate application vulnerabilities, built on learnings from Anthropic's Project Glasswing. It combines threat-modeled discovery, multi-lens adversarial analysis, interprocedural taint analysis, and a beta live-HTTP "exploit verification" stage (S6) that proves exploitability and supports regression-testing fixes via ev-replay, outputting Markdown and SARIF 2.1.0 findings with CVSS/CWE data.

github.comrepoPublished and added 29 Jul 2026🛡️ Security

agentdescent is a Python framework that treats self-improving agents as an optimization problem: N workers propose diffs (edits) to a shared skill/prompt/harness artifact in parallel, and a barrier-free aggregator merges them via conflict resolution, fusion and statistical acceptance rather than gradient averaging, committing winners to a version-controlled ledger. It ships a single `evolve()` entry point with pluggable strategy, scorer, and proposal functions, an MCP server and CLI for agent-triggered runs, and faithful reimplementations of 20 published self-evolution algorithms (ACE, GEPA, EvoSkill, SkillOpt, ADAS, DGM, OpenEvolve, ERA, PromptBreeder, AFlow, Self-Refine, Reflexion, SICA, Gödel Agent, Voyager, SkillWeaver, Absolute Zero, R-Zero, Agent0, Genesis) that plug into the same engine for apples-to-apples comparison. The accompanying paper (Chen, 2026) gives a closed-form condition for when concurrent edits can merge and reports confidence intervals rather than false-precision p-values.

github.comrepoAdded 30 Sep 2026, published 24 Jul 2026🧠 AI

Better Harness is an MIT-licensed plugin/CLI from QoderAI that runs inside a coding agent (Claude Code, Codex, Qoder, Cursor, GitHub Copilot CLI, Qwen Code, Pi, Kimi Code and others) via a /better-harness command. It collects project and session evidence and scores five dimensions of the "Agent Work Loop" (feedforward guides like AGENTS.md, specs and Skills; feedback sensors like linters, tests and Hooks). It outputs HTML/Markdown/Canvas reports with prioritized findings, repair plans and acceptance checks, and keeps missing evidence explicit rather than inventing scores.

github.comrepoAdded 12 Oct 2026, published 21 Jul 2026🧠 AI

Collective Intelligence is an open-source (AGPL-3.0) OpenAI-API-compatible gateway that routes a single request across a continuously-discovered pool of AI models (claimed ~90 provider integrations, 103,224 indexed models) using one of 32 coordination strategies - consensus with convergence floors, blind debate, expert panels, devil's-advocate consensus, cost-cascade, best-of-N with objective verification - instead of sending it to one model. Every response carries an ailin_metadata provenance record (strategy used, models used, cost, dissent), and the repo ships a reproducible benchmark harness with raw per-execution CSVs claiming the coordinated pool beats GPT-5.5-pro, Claude Opus 4.8, Gemini 3.1 Pro and Grok 4.3 on verifiable tasks (97% vs 68-82%). It installs via Docker Compose, exposes an OpenAI SDK-compatible base_url swap, and supports a no-API-key Ollama degraded self-hosted mode.

github.comrepoAdded 2 Oct 2026, published 20 Jul 2026🧠 AI

VulnHunter is Capital One's open-source agentic AI vulnerability scanner built as a set of Claude Code skills (/vulnhunt, /vulnhunter-fix, /vulnhunt-fix-verify) that runs on Claude Opus. Instead of pattern-matching like traditional SAST, it does attacker-first forward analysis from entry points, runs a "falsification engine" to discard unexploitable findings, and generates evidence-backed remediation patches; it also ships a headless agent runtime and a benchmarking harness tested against OWASP NodeGoat, Juice Shop, and WebGoat.

github.comrepoAdded 19 Jul 2026🛡️ Security

NPC-Forge is a framework for building deterministic, non-ML conversational NPCs/agents with multi-turn context, sentiment analysis, and tool-call support, designed to run on CPU even on embedded or obsolete hardware. It ships with an OpenAI-compatible API server so its deterministic agents can be plugged into LLM harnesses like Open WebUI or GitHub Copilot, and includes TERMy, a bundled NPC that transpiles natural-language prompts or scripts into shell commands without using any model. Agents are defined and updated via a dataset format (NDF) rather than trained, with a CLI (npc-forge list/serve/install/reboot) for managing and running them; currently an experimental Linux/WSL-only release under AGPL-3.0.

github.comrepoAdded 30 Sep 2026, published 18 Jul 2026🧠 AI

VulnHunter is Capital One's open-source agentic AI security scanner, implemented as a set of Claude Code skills (/vulnhunt, /vulnhunter-fix, /vulnhunt-fix-verify) that require Claude Opus. Instead of traditional sink-first SAST pattern matching, it reasons forward from attacker-accessible entry points (APIs, uploads, network messages), runs a 'falsification engine' to discard unexploitable findings, and generates evidence-backed exploit paths and targeted code fixes; it also ships a headless agent for CI/CD-scale scanning and a benchmarking harness against corpora like Juice Shop, WebGoat and NodeGoat.

github.comrepoAdded 22 Sep 2026, published 18 Jul 2026🛡️ Security

Mantis is Google's open-source suite of AI agent skills plus an ADK-based reference harness for autonomous security code review. It walks a codebase to build a semantic index and threat model, generates and executes vulnerability research hypotheses across agents, deduplicates and triages findings to combat LLM hallucination, attempts reproduction (static guesses up to spun-up mock servers), chains findings for impact, and patches issues in an adversarial verify-the-fix loop, calibrating severity against a rubric to avoid inflated "critical" spam. It explicitly warns it is demonstration-only, non-deterministic, and requires isolated sandboxing plus human expert verification before any findings are reported.

github.comrepoPublished and added 15 Jul 2026🛡️ Security

garak is NVIDIA's open-source LLM vulnerability scanner, described as an nmap/Metasploit for LLMs that probes generative models for hallucination, data leakage, prompt injection, jailbreaks, toxicity, and other failure modes. It supports a wide range of targets such as Hugging Face, OpenAI, AWS Bedrock, Cohere, Groq, llama.cpp/gguf, REST endpoints, and NIM, and structures scans around pluggable probes, detectors, harnesses, and generators, producing JSONL reports and hit logs.

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

Graft (npm package @nanonets/graft) builds a local, regenerable code graph from a repo — markdown nodes summarizing subsystems plus a per-symbol tree-sitter wiring graph — and wires it into coding agents like Claude Code, Codex, Cursor and Gemini so they no longer re-explore the codebase from scratch every session. It ships an MCP server, CLI commands (ask/grep/callers/skeleton/map/blast/viz), and Claude Code-specific hooks (statusline, blast-radius warnings, auto-resync). The project reports its own benchmarks: a 162-run internal harness and a 50-instance SWE-bench Verified comparison where graft-augmented Claude Sonnet 5 resolved 33/50 instances vs. 27/50 for cold Claude Code, with fewer tool calls, tokens and wall-clock time.

github.comrepoAdded 30 Sep 2026, published 3 Jul 2026🧠 AI

A reference implementation from Anthropic showing how to build a Claude-powered vulnerability discovery and remediation pipeline: interactive skills (/threat-model, /vuln-scan, /triage, /patch, /customize) for static scoping, scanning, triage and patch generation, plus an autonomous seven-stage recon-find-verify-dedupe-report-patch harness that builds targets with Docker/ASAN and runs each agent in a gVisor sandbox with restricted egress. It also ships a detection-and-response track (/dnr-hunt, /dnr-respond) for hunting an attacker already present in logs, scoping blast radius, and proposing a response, demoed against a planted attack campaign in synthetic logs.

github.comrepoAdded 3 Sep 2026, published 5 Jun 2026🛡️ Security

Superpowers is an open-source composable skills library and workflow methodology for coding agents, enforcing a pipeline of brainstorming/spec, plan-writing, subagent-driven or inline TDD implementation, and code review across git worktrees. It ships as a plugin installable into Claude Code, Codex, Cursor, Gemini, Copilot, Grok, and many other agent harnesses, with skills like test-driven-development, systematic-debugging, and writing-plans that auto-trigger during a coding session.

github.comrepoAdded 22 Sep 2026, published 25 May 2026🧠 AI

Tachi is a threat-modeling and AI-reasoning vulnerability detection harness that runs inside Claude Code, dispatching 14 specialized agents against an architecture description (Mermaid, C4, PlantUML, free-text, or ASCII) to find logic-level flaws like broken auth flows, missing privilege boundaries, prompt injection paths, and agent autonomy gaps that SAST cannot catch. It claims full 50/50 coverage across five OWASP frameworks (Web/API, LLM, Agentic, ML, Mobile Top 10s), classifies agentic AI findings against the CSA MAESTRO seven-layer taxonomy, and maps findings to MITRE ATT&CK/ATLAS, NIST AI RMF, and CWE, producing threats.md, SARIF, attack trees, quantitative risk scores, compensating-control analysis, and a PDF security report.

github.comrepoAdded 3 Sep 2026, published 23 May 2026🛡️ Security

FoxGuard is a fast local/CI security scanner offering 200+ built-in rules across 12 languages, cross-file taint tracking for 14 languages, secrets scanning, OSV-backed dependency (SCA) scanning, and a post-quantum crypto (PQC) audit that flags quantum-vulnerable primitives (RSA, ECDSA/DSA, ECDH/DH) against CNSA 2.0 deadlines while also inventorying already-adopted PQC algorithms (ML-KEM, ML-DSA, SLH-DSA, FN-DSA, HQC). It ships a Semgrep/OpenGrep-compatible YAML rule bridge covering ~98% of the public Semgrep registry, outputs to SARIF/CycloneDX 1.6 CBOM/Semgrep-JSON, and integrates via GitHub Action, pre-commit, VS Code, Claude Code plugin, and MCP server, plus an interactive TUI for reviewing findings and baselines. It's part of the "0sec" open cybersecurity harness project.

github.comrepoAdded 3 Sep 2026, published 16 May 2026🛡️ Security

An "Awesome" GitHub list curating research papers, tools, and Claude/Codex "agent skills" focused on LLM-driven vulnerability detection, covering benchmarks (CVE-Bench, VulnGym, SecVulEval), autonomous pentesting/auditing projects (strix, Darkmoon, DeepAudit, AutoCVE, OpenAnt), and vendor-published security-audit skills (Anthropic's defending-code-reference-harness, Cloudflare's security-audit-skill, OpenAI's codex-security). It spans academic work on code-property-graph-guided detection, smart-contract auditing, reinforcement-learning-based reasoning for vuln analysis, and multi-agent false-positive triage.

github.comrepoPublished and added 13 May 2026🛡️ Security

LUKSbox is an open-source (Apache 2.0), pre-1.0 encrypted vault format and CLI/GUI/TUI toolset written in Rust, designed so files can be stored on untrusted cloud/shared media while remaining opaque to the provider. It layers passphrase, FIDO2 hardware authenticators (hmac-secret), and TPM 2.0 sealed keys as unlock factors that all derive a Master Volume Key via HKDF-SHA256, and adds an optional ML-KEM-768/1024 post-quantum sidecar for hybrid encryption. The project publishes its on-disk format spec, threat model, and side-channel notes, and runs libFuzzer/AFL++ harnesses against every parser that touches attacker-controlled bytes (header, keyslot, metadata, hybrid sidecar, WinFsp paths).

github.comrepoPublished and added 8 May 2026🛡️ Security