Security●●Solid
Security Scanner for Agent Skills and MCP
Finally a security linter for MCP configs before you accidentally execute a prompt injection payload.
Solve My ProblemShip It
lirantal
701mo ago
Back to browse
GitHub Repository
Security scanner for AI agent skills. Detects prompt injection, data exfiltration, and malicious payloads before you install.
14 starsPython
SkillGuard – scan agent skills for prompt injection payloads
by arabking·Apr 22, 2026·2 points·1 comment
AI Analysis
●●●BangerSolve My ProblemDark Horse
First open-source scanner for AI agent skill supply-chain attacks.
Strengths
- •Zero dependencies, pure Python 3.10+ makes it easy to integrate anywhere
- •Detects ClawHavoc-style attack patterns like the Lethal Trifecta combination
- •CLI and Python API for both automated CI scanning and manual checks
Weaknesses
- •Very new project with only 2 stars, unproven in production environments
- •Only scans skill files, doesn't monitor runtime agent behavior
Category
Target Audience
AI developers, security teams building with AI agents
Similar To
Snyk · Semgrep · TruffleHog
Similar Projects
Security●●Solid
FireClaw – Open-source proxy defending AI agents from prompt injection
Isolated LLM with no tools or memory makes prompt injection hit a dead end.
Bold BetShip It
raiph_ai
572mo ago
Security●●Solid
Clawned.io Crowdsource public security scanner for OpenClaw skills
60+ threat patterns in sub-2s, but OpenClaw's ecosystem appears niche and unverified.
Solve My ProblemShip It
jensec
123mo ago
Security●●Solid
SkillScan – Free API to detect malicious AI agent skill files
Detects credential theft patterns in AI skill files after ClaudHub attack proved the risk.
Solve My ProblemDark Horse
AutoPilotAI
303mo ago
Security●●●Banger
We scanned 500 ClawHub skills for security risks – 10% were dangerous
19-pattern MCP tool security scanner filling a real gap in agent ecosystem governance.
Solve My ProblemBig Brain
yusufjacobs
313mo ago
Developer Tools●●Solid
Inkog – Pre-flight check for AI agents (governance, loops, injection)
Catches infinite loops and injection risks without running the agent, but Snyk+Semgrep+manual review already covers this.
Solve My ProblemShip It
benban
123mo ago