Enhanced malicious Skill detection tool. Analyzes whether a target skill poses security threats to users who install it.
-
Updated
Mar 19, 2026 - Python
#
skill-security
Here are 27 public repositories matching this topic...
AVE - Agentic Vulnerability Enumeration. The open behavioral classification standard for agentic AI components.
taxonomy mcp owasp vulnerability ave devsecops ai-agents behavioral-patterns security-research ai-security supply-chain-security llm prompt-injection llm-security agentic-ai mcp-server agent-security mcp-security aivss skill-security
-
Updated
Nov 7, 2026 - Python
Three portable Agent Skills for research, repository deployment, and pre-install safety review.
-
Updated
Aug 5, 2026 - Python
Open-source CLI scanner for agentic AI components such as skills, MCP servers, system prompts
mcp owasp security-scanner devsecops vulnerability-scanner ai-security prompt-injection llm-security agentic-ai agent-security mcp-security aivss skill-scanner skill-security ai-skill-scanner mcp-scanner agent-linter toxic-flows
-
Updated
Oct 25, 2026 - Python
SQS (Skill Quality Suite): linter, validator, security scanner and eval harness for AI Agent Skills (SKILL.md) on Claude Code, Codex, Cursor and Gemini CLI - and it tells you which skill to fix or write next from your own sessions
linter static-analysis pre-commit cursor codex sarif ai-agents github-actions skill-evaluation secret-scanning supply-chain-security prompt-injection llm-evaluation gemini-cli agent-skills claude-code claude-skills skill-security skill-validator skill-lint
-
Updated
Nov 3, 2026 - Python
Decide once. Re-decide never. A Claude Code skill that evaluates skills before installing and persists every decision.
ai-agents anthropic agent-skills claude-code claude-code-plugin claude-skills skill-registry skill-security skills-curator skill-judgment skill-evaluator
-
Updated
Oct 18, 2026 - Python
AI security toolkit for prompt injection detection, sensitive data protection, runtime monitoring, and threat intelligence for LLM and agent workflows.
cybersecurity threat-intelligence runtime-monitoring ai-security prompt-injection llm-security sensitive-data-detection agent-security openclaw skill-security
-
Updated
Apr 7, 2026 - Python
LGD ecosystem: independent third-party evaluation for AI agent skills. Registered / Evidenced / Gated - a score that ends in a permission decision.
static-analysis openai security-scanner devsecops ai-security supply-chain-security trust-score ai-agent ai-governance llm-security agentic-ai agent-security mcp-security claude-skills skill-security
-
Updated
Nov 7, 2026 - Python
Audit AI skill safety before you ship. Static + semantic + adversarial audit pipeline for SKILL.md, Codex skill.yaml, Claude Code commands, and OpenCode. Free hosted tier on tarai.dev.
skill mcp audit ai-safety aisafety model-context-protocol aiskills claude-skill codex-skill openclaw-skill skill-security skill-audit ai-agent-safety ai-skill-safety audit-ai-skill ai-skill-audit
-
Updated
Nov 7, 2026 - Python
Public scorecards and leaderboard for evaluated AI agent skills. Reproducible evidence, not marketing claims.
benchmark security-audit leaderboard evaluation ai-security trust-score ai-agent ai-governance mcp-security skill-security
-
Updated
Nov 6, 2026 - Python
Security auditor for AI agent skills — catches hidden-Unicode prompt injection, reviewer-subversion, data exfiltration & post-install drift that markdown-only vetters miss.
python security skills mcp static-analysis security-scanner ai-safety security-tools devsecops ai-agents claude supply-chain-security prompt-injection anthropic llm-security mcp-server agent-skills claude-code skill-security skill-vetting
-
Updated
Jul 1, 2026 - Python
See what your AI-agent skills can actually do. Vouch audits every SKILL.md on your machine, explains each skill's capabilities in plain English, and flags the risky ones (destructive commands, secret exfiltration, prompt injection). Local, deterministic — like npm audit, but for agent skills.
python cli skills mcp static-analysis developer-tools cursor security-scanner security-tools ai-agents claude malware-detection sast ai-security supply-chain-security llm prompt-injection llm-security agent-security skill-security
-
Updated
Sep 9, 2026 - Python
Static security scanner for agent skills: A-F risk rating, safe zip scanning, CI-tested rules
security skill scanner static-analysis audit ai-agent agent-security openclaw skill-security deepseek-harness dsh-plugin
-
Updated
Sep 1, 2026 - Python
One score, one permission tier. Static security + quality gate for AI agent skills (Claude Skills / MCP). Detects credential exfiltration, base-URL hijack, shell payloads.
static-analysis ci-cd openai code-review security-scanner devsecops sast ai-security github-action supply-chain-security trust-score ai-agent ai-governance prompt-injection llm-security agentic-ai agent-security mcp-security claude-skills skill-security
-
Updated
Nov 6, 2026 - Python
A curated AI coding skill and hook pack for safe local workflows.
productivity security automation developer-tools code-review summarization code-quality memory-management red-team ai-agents claude llm prompt-engineering anthropic agent-skills claude-code adversarial-testing claude-code-plugins claude-code-skills skill-security
-
Updated
May 20, 2026 - Python
Static safety scanner for AI agent skills: detect prompt injection, curl-pipe-sh malware, credential theft before you install.
opencode ai-agents malware-scanner supply-chain-security prompt-injection agent-skills claude-code skill-security
-
Updated
Oct 1, 2026 - Python
Claude Code skills for keeping a Claude Code setup safe: review a third-party skill before installing it, lint and evaluate your own skill descriptions, audit the context budget, build least-privilege permissions, author and test hooks, find skill collisions and portability problems. Drives the author's gate, lock, simulator and hook tools.
python hooks linting permissions developer-tools hacktoberfest ai-agents ai-security supply-chain-security agent-skills claude-code context-engineering claude-code-plugin claude-skills claude-code-skills skill-security
-
Updated
Nov 2, 2026 - Python
Codex Skill：审计 Skill 和 AI agent 工具包的脚本、密钥、外部网络、权限边界与供应链风险
security-audit developer-tools secret-scanning plugin-security supply-chain-security ai-governance prompt-injection skill-marketplace ai-agent-security codex-skill skill-security
-
Updated
Jul 7, 2026 - Python
Static security scanner for AI skills, agents, prompts, and MCP instruction files
-
Updated
Jul 14, 2026 - Python
Independent, local-only watcher for the AI-skill supply chain: flags bait-and-switch changes in the pages skills and MCP tools reference. Sends nothing anywhere. Python CLI.
python cli mcp security-tools devsecops ai-agents bait-and-switch ai-security supply-chain-security prompt-injection llm-security url-monitoring mcp-security homoglyph-detection skill-security
-
Updated
Oct 15, 2026 - Python
Add this topic to your repo
To associate your repository with the skill-security topic, visit your repo's landing page and select "manage topics."