skillhawk
Catch dangerous AI agent skills before they catch you. Zero-dependency security scanner for Agent Skills, SKILL.md and MCP configs.
Berserk-hub150/skillhawk
View on GitHub ↗Catch dangerous AI agent skills before they catch you. Zero-dependency security scanner for Agent Skills, SKILL.md and MCP configs.
skillhawk grew +80.3% in the last 30 days, ranks 653rd of 872 in Evaluation & Guardrails, actively maintained, last commit today.
Star trajectory
67 days tracked+80.3% in 30d, above the Evaluation & Guardrails median of +1.4%.
Last commit today, fresher than the median of 15d.
How it compares in Evaluation & Guardrails
Ranked 653rd of 872 by stars.
Related repos
Ranked by shared tags, then keywords, then starsWhere skillhawk sits
Hover or focus a node for details. Click to open it.
- This repo
- Related repo
- Tag or category
Semia, security audit for AI agent skills.
+1 (+0.2%) in 30d · Committed 81d ago · Python · Apache-2.0
Shares Evaluation & Guardrails, Tools & Integrations, Agent Skills
The missing linter and lsp for AI coding assistants. Validate CLAUDE.md, AGENTS.md, SKILL.md, hooks, MCP…
+37 (+8.1%) in 30d · Committed today · Rust · Apache-2.0
Shares Evaluation & Guardrails, Tools & Integrations, Agent Skills
Claude Code-style declarative permission rules for DeepSeek Harness: ordered allow/deny/ask rules with…
+21 (+18%) in 30d · Committed today · TypeScript · Apache-2.0
Shares Evaluation & Guardrails, Tools & Integrations, Agent Skills
Offline cyber security agent for your apps and AI coding tools. Open R&D: measured in public, improved every…
+62 (+117%) in 30d · Committed today · JavaScript · MIT
Shares Agent Skills, Tools & Integrations, Evaluation & Guardrails
SAIL V2 (Secure AI Lifecycle) as an agent skill — the full 91-risk catalog for AI/agent gap assessments…
-5 (-4.5%) in 30d · Committed 137d ago · Other license
Shares Tools & Integrations, Evaluation & Guardrails, Agent Skills
AI design system scanner + mcp server. Scores repos 0-100, writes fix prompts. 30K+ npm downloads.
Committed 14d ago · JavaScript · MIT
Shares Evaluation & Guardrails, Agent Skills, Tools & Integrations
Agent-Native multi-platform reverse engineering and CWE-602 client-side authorization audit workbench.
+461 (+25%) in 30d · Committed today · Lua · GPL-3.0
Shares Tools & Integrations, Agent Skills, Evaluation & Guardrails
Enterprise-grade deep research skill for Claude Code with 8-phase pipeline, source credibility scoring, and…
+28 (+2.3%) in 30d · Committed 224d ago · Python
Shares Tools & Integrations, Evaluation & Guardrails, Agent Skills
SkillSpec makes agent skills followable, testable, and provable with Doctor risk reports, guided imports…
-59 (-8.4%) in 30d · Committed 104d ago · Rust · Apache-2.0
Shares Evaluation & Guardrails, Tools & Integrations, Agent Skills
Give AI agents eyes, ears, and verifiable results. Watch Skill turns video, audio and screen activity into…
+83 (+16%) in 30d · Committed 5d ago · Python · MIT
Shares Tools & Integrations, Evaluation & Guardrails, Agent Skills
- Language
- JavaScript
- License
- MIT License
- Contributors
- 25
- Forks
- 56
- Watchers
- 0
- Open issues
- 45
- Releases
- 4
- Created
- 2026-08-16
- Stars this week
- +20
You've seen where skillhawk stands today.
Get the moves before everyone else: the 5 Evaluation & Guardrails repos climbing fastest, every Tuesday.
Free weekly digest. Double opt-in, unsubscribe anytime.