Skip to content

35 results for “AX”

ListGrid
What you seeeverything
RecentOldestAddedA–Z
All types340Articles136Papers102Write-ups36Repos35
Threads13Advisories6Tools6Talks4Courses1Other1
📦 Repos“AX”Clear all
github.comrepo🧠 AI

rikugan: LLM reverse-engineering agent for IDA Pro and Binary Ninja

Rikugan is a reverse-engineering agent that runs inside IDA Pro and Binary Ninja. It has its own generator-based agent loop, context management, plan mode and 60+ tools, and does not depend on an external MCP server. An orchestrator spawns parallel subagents to analyze a binary. It supports Anthropic, Gemini, MiniMax, Kimi, OpenAI-compatible endpoints and Ollama, with per-model notes.

IDA ProBinary NinjaHex-Rays+6
RikuganClaude Opus 4.6Claude Sonnet 4.6+6

agents, coding-agents· Added 30 Oct 2026

github.comrepo🛡️ Security

rikugan: LLM reverse-engineering agent for IDA Pro and Binary Ninja

Rikugan is an open-source reverse-engineering agent that runs inside IDA Pro 9.0+ and Binary Ninja, with its own agent loop instead of an MCP server. It has 60+ tools (decompiler, xrefs, strings, types, IL/microcode), parallel subagent exploration, an experimental /modify natural-language patching command and an experimental Binary Ninja deobfuscation skill for control flow flattening and opaque predicates. It supports Claude, Gemini, MiniMax, Kimi, OpenAI-compatible endpoints and Ollama.

IDA ProBinary NinjaLLM+3
control flow flatteningopaque predicatesMBA expressions+1

Malware & RE, AI Security· Added 30 Oct 2026

github.comrepo🛡️ Security

OWASP/MCP-Security-Testing-Guide

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.

Model Context ProtocolLLM
OWASPMCP Goat

AI Security, AppSec· Added 17 Oct 2026

github.comrepo🧠 AI

alex09x/kyb

KYB (Know Your Business) is a Rust/axum server that stores agent-written knowledge, incident reports and tasks as Markdown files in Git, one commit per change. Search is hybrid: Tantivy BM25 fused by reciprocal rank with local multilingual-e5-small ONNX vectors, and it can query historical versions or "as of" a date. It ships a kyb CLI, a native MCP endpoint (Claude Code, Codex, Antigravity, Gemini CLI), an installable agent skill, token auth with per-write attribution trailers, secret scanning on writes, and a web console. It targets persistent shared operational memory for multi-agent, multi-machine fleets.

RustGitModel Context Protocol+10
KYBAlexander Panasenkomultilingual-e5-small

agents, mcp, coding-agents· Added 17 Oct 2026

github.comrepo🧠 AI

Show HN: Atticus – Hold-to-talk voice assistant for macOS that runs on Claude -p

Atticus is an MIT-licensed macOS 26+ hold-to-talk voice assistant that uses Apple's on-device speech transcription and runs AI requests through Claude Code on an existing Claude Pro/Max plan, so no API key is needed. Simple commands skip the model entirely (apps open in 0.08 s), actions it has seen once are learned as zero-cost shortcuts, and a "remember…" memory persists across asks. It also sets up no-AI background watchers (polling every 5 s) and holds itself to a budget of a median under $0.002 and 6 s per AI ask, with a system prompt under 10,000 characters.

Claude CodeClaudeCodex+6
AtticusAnthropicApple+1

agents, coding-agents, multimodal· Published and added 12 Oct 2026

github.comrepo🧠 AI

Bifrost (Maxim AI) — open-source LLM gateway

Bifrost is an open-source, high-performance LLM gateway (by Maxim AI) that exposes a single OpenAI-compatible API across 23+ providers including OpenAI, Anthropic, AWS Bedrock, Google Vertex, Azure, Cohere, Mistral, and Ollama. It provides automatic failover, load balancing, semantic caching, Model Context Protocol (MCP) tool integration, budget and governance controls, OIDC user provisioning, and Prometheus-based observability, deployable via npx or Docker with claimed sub-15 microsecond overhead at 5,000 RPS. It is positioned as a drop-in replacement requiring only a base-URL change for existing OpenAI, Anthropic, or GenAI SDK code.

DockerGoModel Context Protocol+4
Maxim AI

ai-infra, mcp· Added 2 Oct 2026

github.comrepo🛡️ Security

NuvexNetwork/nuvex

Nuvex is a Solana-native verifiable compute and oracle protocol, still pre-mainnet, whose own README documents unresolved security gaps instead of hiding them: its VRF proof verification relies on solana-ecvrf 0.0.1 (RFC 9381 ECVRF-Edwards25519-SHA512-TAI) which has no known audit, max_fee is stored but never actually charged, and VRF fulfillment is first-come among any node meeting the configured stake/heartbeat threshold — meaning an operator who funds several keys at a low minimum stake can selectively pick which randomness output gets used. The deploy-mainnet script is stubbed to exit before any transaction, and unresolved design questions (fee shares, challenge/reject state transitions) are tracked as explicitly blocked ADRs rather than quietly shipped.

SolanaRust
solana-ecvrfRFC 9381ECVRF-EDWARDS25519-SHA512-TAI

Blockchain· Published and added 2 Oct 2026

huggingface.corepo🧠 AI

Ternary-Bonsai-2-27B: 27B model compressed to ~1.75 bits/weight, 98.2% of FP16 quality retained

Ternary-Bonsai-2-27B is a 27B-parameter reasoning model (built on Qwen3.8-27B) quantized to true ternary weights ({-1,0,+1}) at ~1.72 bits/weight, shrinking it from ~54GB FP16 to ~5.95GB while retaining 98.2% of FP16 benchmark quality (84.78 vs the conventional sub-4-bit IQ2_XXS build's 72.59). It uses a Hadamard-rotated weight basis and ships two GGUF packing formats (PTQ1_0 dense trits, PQ2_0 2-bit slots) that require a custom llama.cpp/MLX kernel fork since stock llama.cpp cannot decode them correctly. The card includes per-category benchmark breakdowns (math, coding, agentic tool calling), cross-platform throughput/power measurements (Apple M5 Pro/Max, RTX 5090, L4, H100/A100/Blackwell), and an "intelligence density" metric comparing capability retained per GB against FP16 and other quantizations.

GGUFllama.cppvLLM+8
Prism MLGemma-4-31BMMLU-Redux+3

models, inference· Added 29 Sep 2026

github.comrepo🧠 AI

vLLM v0.30.0

Release notes for vLLM v0.30.0, a major update to the open-source LLM inference/serving engine spanning 762 commits. Highlights include new model support (DeepSeek-V4.1-Flash, GLM-5.3-Flash, Kimi K3, Qwen3.8-Flash-Next, K2-Horizon, Cohere Compass and others), a "Fast Start" GPU weight-cache daemon for near-instant engine restarts via CUDA IPC, Gumbel-max watermarking for generated text, a HiSparse host-memory tier for sparse-MLA KV offload, Model Runner V2 improvements (dual-batch overlap, speculative decoding under pipeline parallelism), expanded quantization support (NVFP4, W4A16 DSA, AutoRound), and hardware-specific tuning across NVIDIA, AMD ROCm, Intel XPU and CPU backends.

vLLMCUDAFlashInfer+9
DeepSeek-V4.1-FlashDeepSeek-V4-Flash-Vision-ExpGLM-5.3-Flash+16

inference, models· Added 28 Sep 2026

github.comrepo🛡️ Security

Adversarial-Detection-Engineering/adeskills

adeskills is a working knowledge base for "Adversarial Detection Engineering" (ADE), a taxonomy of four categories and 16 subcategories of detection-logic bugs (e.g. Reformatting in Actions, Omit Alternatives, Context Development, Logic Manipulation) that explain why a SIEM/EDR/XDR rule fails to catch what it intends to. It ships 38 worked technique files with vulnerable/hardened rule examples and detection-layer guidance, a cross-platform bug-pattern catalog, a pre-engagement scoping checklist, and a Redamon-packaged skill (ade_scoper), all grounded in analysis of real public rulesets from Sigma, Elastic Security, and Microsoft Sentinel. It's explicitly scoped for defensive detection engineering and purple-team rule hardening, with several files documenting real vendor-rule weaknesses.

SigmaMicrosoft SentinelElastic Security+3
Nikolas BielskiDaniel Koifman

Blue Team & Detection· Added 2 Oct 2026, published 27 Sep 2026

github.comrepo🛡️ Security

MITRE ATLAS v2026.09 data release

Release changelog for MITRE ATLAS's atlas-data repository, the structured YAML/STIX dataset behind the ATLAS knowledge base of adversary tactics and techniques targeting AI-enabled systems (prompt injection, model/data poisoning, AI agent tool abuse, AI supply chain compromise). The v2026.09 release brings the matrix to 120 techniques, 88 sub-techniques, 40 mitigations, and 73 case studies, and recent versions introduced a new v6 YAML data format with Pydantic/SQLAlchemy/FastAPI tooling, platform tagging (Predictive AI, Generative AI, Agentic AI, Enterprise), and renamed/generalized techniques like "AI Agent Tool Poisoning," "Manipulate AI Model," and "Enterprise Resource Discovery." It's the canonical, actively-maintained taxonomy practitioners use for AI red-teaming, threat modeling, and mapping real-world AI attack case studies.

MITRE ATLAS
AML.T0019AML.T0058AML.T0104

AI Security· Added 26 Sep 2026

github.comrepo🧠 AI

google/ax — declarative agentic orchestration runtime

AX is Google's declarative orchestrator for running large numbers of autonomous agent workloads on Kubernetes, built on top of "Agent Substrate" for sandboxed execution. Agents are declared via YAML manifests (Task, Workspace, Model) similar to kubectl, and applied with an `ax` CLI that supports apply/get/watch/ssh/suspend/resume, treating agent runs as a distinct workload type distinct from stateless services or batch jobs.

KubernetesGoDocker+2
GoogleAgent Substrate

agents, ai-infra· Added 26 Sep 2026

github.comrepo🛡️ Security

CVE-2026-26980 — Ghost CMS Content API unauthenticated blind SQLi lab

A Docker-based exploitation lab for CVE-2026-26980, an unauthenticated blind SQL injection in Ghost CMS's Content API (versions before 6.19.1). The bug lives in slug-filter-order.js, where slug values from the array-notation filter syntax (filter=slug:['value']) are interpolated unsanitized into an ORDER BY CASE statement, letting NQL's single-quote-wrapped literals smuggle raw SQL past input validation; since MySQL treats || as OR and empty strings as falsy, attackers get a clean boolean oracle to extract data (e.g. admin email/password hash) from any Ghost site using only the publicly embedded Content API key. The repo includes exploit.py for full setup/verify/extract, a docker-compose lab spinning up both vulnerable (6.18.0) and patched (6.19.1) Ghost instances, and also mentions a second patched bug (jsonpath/static-eval prototype pollution in the {{#get}} Handlebars helper leading to RCE via themes).

Ghost CMSMySQLPython+1
CVE-2026-26980CWE-89

AppSec, Offensive Security· Added 21 Sep 2026

github.comrepo🛡️ Security

agent-egress-bench

Agent Egress Bench is an open, tool-neutral benchmark maintained by PipeLab (makers of Pipelock) that tests whether products mediating an AI agent's outbound traffic — proxies, egress firewalls, MCP wrappers, agent gateways — actually catch exfiltration attempts caused by prompt injection or misalignment, rather than testing the underlying model itself (that's left to AgentDojo, InjecAgent, CyberSecEval, AgentHarm, ASB). It ships a reproducible Go runner with a proxy/WebSocket/MCP/A2A adapter contract, an offline validator, DSSE-signed evidence bundles, and a CI-runnable GitHub Action, and separates containment from false-positive rate as two distinct scored axes with immutable case IDs and OWASP Agentic Top 10/MITRE ATT&CK mappings. Its governance explicitly permits third parties to publish results unfavorable to the maintainer's own Pipelock product.

Model Context ProtocolGoDocker+2
AgentDojoInjecAgentCyberSecEval+6

AI Security, Blue Team & Detection· Added 12 Sep 2026

github.comrepo🛡️ Security

AWSHound — AWS BloodHound OpenGraph Collector

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.

AWSAWS IAMBloodHound+2

Cloud & Infra, Offensive Security· Added 8 Sep 2026

github.comrepo🛡️ Security

0x4D31/endpoint-ai-agent-abuse

endpoint-ai-agent-abuse (EAA) is a curated, evidence-scoped taxonomy of techniques for abusing local, endpoint-resident AI agents — especially coding and developer agents — covering launchers/flags, provider routing, instructions, memory, hooks, plugins, skills, MCP, transcripts, telemetry, and inherited local-user authority. Each technique is tagged by maturity (feasible, demonstrated, observed) and backed by cited incidents, artifacts, or research, with companion files for surfaces, tactics, case mappings, and detection/hunting hypotheses plus a validator script and JSON schema for the catalog.

Model Context Protocol

AI Security· Published and added 7 Sep 2026

github.comrepo🧠 AI

emlai/defi-native-skill

An open-source Agent Skill ("defi-native") that teaches Claude Code, Cursor, Codex and other Agent-Skills-compatible agents capital-markets and DeFi domain knowledge, including yield decomposition, vault/curator anatomy, oracle classes, and stablecoin/RWA taxonomy. It is structured with progressive disclosure (SKILL.md routes to task-specific reference files only when needed), an api-routes.json router that forces live data pulls (vaults.fyi, DefiLlama, Morpho's GraphQL, rwa.xyz, Merkl, 130+ protocol docs) before any numeric claim, and a verified 90+ source manifest. The author describes an eval-gated release process (paired with/without-skill runs graded on structure) and adversarial review by independent models before publishing, making it a useful case study in skill engineering even for readers uninterested in DeFi itself.

Claude CodeCursorCodex+1
Emily Lai

prompting· Added 2 Oct 2026, published 28 Aug 2026

github.comrepo🛡️ Security

henrymao2004/Auto-research-red-teaming

AHA (Agent Hacks Agent) is an autonomous red-teaming framework where a researcher agent iteratively hypothesizes attacks, runs them against Docker-sandboxed victim agents (built on Claude Code and Codex, targeting frontier models like Minimax-M2.7, Kimi-K2.6, and Deepseek-V4-Pro), and accumulates a persistent Vulnerability Concept Graph of reusable attack mechanisms rather than one-off jailbreak strings. It reports held-out Attack Success Rate evaluations showing these mechanisms — notably a "claimed-authorization" bypass pattern — transfer across scenarios and victim models (up to ~88% of native ASR), and ships as registry-discovered plugins for scenarios like AgentHazard, AgentDojo-style indirect injection, and DecodingTrust-Agent.

Claude CodeCodexDocker+2
AgentHazardAgentDojoDecodingTrust-Agent+2

AI Security, Offensive Security· Published and added 25 Aug 2026

github.comrepo🛡️ Security

opaxial/CVE-2026-9830

A Python proof-of-concept (CVE-2026-9830) that validates an unauthenticated REST API exposure in the BookingPress Pro WordPress plugin, where unauthenticated requests to a booking endpoint can return customer PII such as names, emails, phone numbers, and booking details. The script supports non-invasive checking, proxy/timeout/user-agent configuration, booking ID and date filtering, and optional saving of retrieved responses, alongside guidance for responsible use and remediation (patching, enforcing auth/capability checks on REST routes, log review, and incident response).

WordPressPythonBookingPress
CVE-2026-9830

Offensive Security, AppSec· Added 2 Oct 2026, published 15 Aug 2026

github.comrepo🛡️ Security

SiberKapan

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.

MISPFortiGateSuricata+3
CISA KEVAbuseIPDBMalwareBazaar+1

Threat Intel, Blue Team & Detection· Published and added 8 Aug 2026

github.comrepo🧠 AI

deepbeepmeep/Wan2GP

WanGP (Wan2GP) is an open-source 'super app' that packages dozens of open generative video, image, audio and TTS models (Wan, MiniMax H3, LTX-2, Qwen Image, Krea 2, SeedVR2, etc.) behind a single web UI, optimized to run on as little as 6GB VRAM including older Nvidia and AMD GPUs. It bundles LoRA support, quantized checkpoint formats (int8, fp8, GGUF, NVFP4), an agentic assistant ('Deepy') for orchestrating generation jobs, a plugin system, and a headless/API mode for batch and programmatic use.

GGUFLoRANunchaku+3
WanGPWan2GPDeepBeepMeep+7

multimodal, inference, mcp· Added 22 Sep 2026, published 30 Jul 2026

github.comrepo🛡️ Security

RamanMG/Burp-MCP-Unrestricted

An unofficial fork of PortSwigger's Burp Suite MCP server extension that removes the human-approval prompts before an AI client can send HTTP requests or read captured proxy data, and adds tooling aimed at long unsupervised engagements: newest-first proxy history, site map access, scan/crawl driving, and Repeater automation via direct Swing UI manipulation. It also removes the upstream 5000-character response truncation (configurable via maxLength) that could otherwise hide large findings like stack traces or GraphQL introspection dumps from an agent.

Burp SuiteModel Context ProtocolClaude Desktop+1

Offensive Security, AI Security· Published and added 29 Jul 2026

github.comrepo🛡️ Security

DevCop95/shodan_reconsx

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.

PythonShodanPowerShell

OSINT· Added 30 Sep 2026, published 29 Jul 2026

github.comrepo🧠 AI

yolorouter/yolorouter

Yolorouter is a free, self-hosted, single-binary LLM gateway that translates between the four major chat wire protocols — OpenAI Chat Completions, OpenAI Responses, Anthropic Messages, and Gemini generateContent — so a client built for one provider (e.g. Claude Code) can be pointed at any other. It adds multi-provider failover, round-robin upstream API key pooling with rate-limit/quota handling, per-key budgets and access control, a multi-user admin console with OAuth2/OIDC SSO, and native image/video generation support for OpenAI-shaped and non-OpenAI-shaped providers (DashScope, Volcengine Ark, Kling, MiniMax). It also ships cost-optimization features — deterministic system-prompt injection and tool-output compression for coding agents — backed by a published benchmark, plus built-in usage/cost observability.

DockerGoSQLite+4
YolorouterOpenAIAnthropic+11

ai-infra· Added 2 Oct 2026, published 21 Jul 2026

github.comrepo🛡️ Security

AI Security Briefing

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).

QwenLlama Guard 3WildGuard+1
OWASPAgentDojoInjecAgent+3

AI Security· Published and added 19 Jul 2026

github.comrepo🛡️ Security

OpenNVR

OpenNVR is a self-hosted, Docker-deployed network video recorder for ONVIF/RTSP IP cameras that is explicitly designed around a "sovereign, air-gapped by default" security architecture: network isolation between camera/gateway/analytics planes, Fernet-encrypted credentials at rest, RTSPS transport, and two default-deny gates (DEPLOYMENT_MODE=offline, AI_SOVEREIGNTY=local_only) that keep cloud and AI egress returning HTTP 403 until explicitly opened. It's positioned as a response to systemic IP-camera weaknesses (default creds, hard-coded keys, unsigned firmware, vendor cloud aggregation) exploited historically by the Mirai botnet and the 2021 Verkada camera-feed breach, and targets regulated buyers newly barred from Hikvision/Dahua/Uniview/Edimax-class vendors under NDAA §889 and 2025-26 FCC enforcement. Its pluggable AI Adapter Contract (Apache-2.0 SDK) lets third parties add detection/LLM capabilities out-of-tree, with correlation-ID audit trails and SHA-256 model fingerprinting for compliance evidence.

DockerOllamaPython
MiraiVerkadaNDAA §889+4

Hardware & RF· Published and added 18 Jul 2026

github.comrepo🛡️ Security

ZX41R/awesome-reverse-engineering-and-malware-analysis

A curated, upkept "awesome list" for reverse engineering and malware analysis that organizes hundreds of resources into guided learning tracks (Windows malware triage-to-config-extraction, Linux/ELF reversing, exploit development, firmware & embedded, mobile, anti-analysis) plus a full taxonomy covering foundations, RE tooling (IDA, Ghidra, Binary Ninja, radare2, x64dbg), malware analysis/unpacking/YARA/C2 tracking, fuzzing (AFL++, libFuzzer), firmware, mobile, OS internals, LOLBAS/GTFOBins living-off-the-land resources, DFIR, and threat intelligence. It also surfaces niche researcher communities like Kanxue, 52pojie, Tuts4You, the WASM Russian RE forum, 0x00sec, and back.engineering (VTIL/VMProtect devirtualization work), with every link manually vetted and dead links pruned.

GhidraIDAradare2+3
VMProtectVTILKanxue+3

Malware & RE, Offensive Security, Hardware & RF· Added 30 Sep 2026, published 6 Jul 2026

github.comrepo🛡️ Security

ThinkWatch

ThinkWatch is a source-available dual-port gateway (Rust/Axum) that proxies both AI provider APIs (OpenAI, Anthropic, Gemini, Azure OpenAI, AWS Bedrock) and MCP tool calls through a single control plane, enforcing authentication, RBAC, rate limits/budgets, and audit logging. Its key differentiator is per-user upstream identity for MCP — propagating each user's own OAuth token/PAT to servers like GitHub/Notion/Slack (AES-256-GCM encrypted, per-key allowlists) instead of a shared service account, plus SSRF-hardened OAuth discovery (RFC 9728/8414/7591), tool-level RBAC, and ClickHouse-backed audit trails forwarded to SIEMs via Syslog/Kafka/webhooks.

Model Context ProtocolOAuthOIDC+3
RFC 9728RFC 8414RFC 7591

AI Security, Identity & Access· Published and added 4 Jul 2026

github.comrepo🛡️ Security

Tencent/AI-Infra-Guard

AI-Infra-Guard (A.I.G) is Tencent Zhuque Lab's open-source AI red-teaming platform that fingerprints running AI services (e.g. vLLM, LangFlow, MLflow, llama.cpp) against a library of 2000+ CVE rules, scans MCP servers and Agent Skills for vulnerabilities using the SkillTrustBench T01–T09 taxonomy, and runs multi-turn jailbreak evaluations (Many-Shot, PAIR, GOAT, ActorAttack). It also ships an LLM API poisoning/model-substitution detector, a plugin framework for community-contributed fingerprint/vuln/MCP rules, and accompanying research (FORGE-Bench, RogueHandoff-20, SkillJack) on agent loss-of-control and skill backdoors.

Model Context ProtocolvLLMllama.cpp+3
SkillTrustBenchFORGE-BenchRogueHandoff-20+7

AI Security· Added 2 Jul 2026

github.comrepo🛡️ Security

XORCISM-AI/XORCISM

XORCISM is a self-hosted, open-source enterprise risk/exposure management platform (Node.js/TypeScript over SQLite/PostgreSQL/MySQL) that unifies asset inventory, vulnerability management, threat intel (STIX/TAXII), GRC (ISO 27001, NIST CSF/800-53, EBIOS Risk Manager, NIS2, DORA), incident management, and offensive/defensive testing into one continuously recomputed per-asset and enterprise risk score. It chains recon/exploitation tool connectors (nmap, nuclei, Metasploit, sqlmap) into attack-path/choke-point graphs weighted by fusion exploitability (EPSS+CVSS+KEV+public exploits), validates detection coverage via a purple-team loop against 3,750+ Sigma rules and MITRE ATT&CK/D3FEND, and quantifies ransomware impact in dollar terms via a FAIR-style model — with local-only Ollama AI assistants for triage, hunting, and reporting.

Node.jsTypeScriptSQLite+3
APT29SecureCodersRustinel

GRC, Offensive Security, Blue Team & Detection· Published and added 1 Jul 2026

Showing 30 of 35

Show more