25 packages found
Backdooring Claude Code via hooks in settings.json. Authorized use only!
历年ICLR论文和开源项目合集，包含ICLR2021、ICLR2022、ICLR2023、ICLR2024、ICLR2025.
AI code security scanner MCP server — detects invisible Unicode, Trojan Source, homoglyphs, Glassworm steganography, rul
[NeurIPS 2024] Official implementation for "AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Po
Trust nothing. Ship safely. — Skeptical-reading and prompt-injection defense skill for AI agents. Provenance tagging, re
Security scanner for MCP servers - detect backdoors, exfiltration, and prompt injection
Agent orchestration & security template featuring MCP tool building, agent2agent workflows, mechanistic interpretability
Official companion repository for our survey "A Survey of the OpenClaw Ecosystem: From Platform Extensibility to Constra
Universal preflight security scanner for AI coding agents — Detects hooks injection, credential exfiltration & backdoors
AI-native ontology engine: a Rust MCP server with tools for building, validating, querying, and reasoning over RDF/OWL o
A repo lists papers related to LLM based agent
AI-first security scanner with 79 analyzers, 40,000+ detection rules, and repo poisoning detection for AI/ML, LLM agents
Ultra-Fast Python Solutions: 110x Speed Optimization Guide 2026
GitHub Actions & CI/CD security scanner. Detects 30+ attack patterns including HackerBot-Claw campaign vectors. CLI + MC
Security infrastructure your AI can't be — deterministic, daily CVE intel past your model's training cutoff, whole-repo-
Deterministic music-theory MCP server & API — chord analysis, Roman-numeral analysis, voicing & reharmonization for Clau
Local guardrails for AI coding agents. Wraps any MCP server and blocks destructive tool calls — DROP TABLE, rm -rf, forc
Find vulnerabilities. Ship secure. — Senior security-engineer skill for AI coding agents. OWASP Top 10, CWE Top 25, secr
It is a comprehensive resource hub compiling all LLM papers accepted at the International Conference on Learning Represe
Lasso security integrations for Claude Code, including prompt-injection defenses
AI agent firewall that intercepts tool calls (file, shell, network) and enforces deterministic policies at sub-microseco
Multi-agent orchestration for Claude Code with 15-30% token optimization, self-improving agents, and automatic verificat
Open-source permission control plane for AI agents. Scan, enforce, and audit every tool call.
Opinionated defaults, documentation, and workflows for Claude Code at Trail of Bits
A growing collection of MCP servers bringing offensive security tools to AI assistants. Nmap, Ghidra, Nuclei, SQLMap, Ha