Claude MarketplacesSubmit

SkillAudit

megamind-0x/skillaudit

A security scanner that checks AI agent skills and MCP servers before your agent installs them. It runs 43 detection rules across 401 patterns, catching credential theft, data exfiltration, prompt injection, obfuscated code, and container escapes. You get a free API with gate checks (allow/deny decisions), full scans, policy enforcement, and MCP manifest analysis for schema poisoning. The CLI works as npx skillaudit with zero config, or as an MCP server tool in Claude Desktop. It returns risk scores (clean/low/moderate/high), outputs SARIF for CI/CD, and includes GitHub Action integration. Premium deep scans with threat chain analysis run on x402 micropayments. Reach for this when you need to gate third party skills in autonomous agent workflows or enforce security policy in agent deployment pipelines.

tools: 5
transport: HTTP
last updated: Feb 15, 2026

Tools

5 tools

Public tool metadata for what this MCP can expose to an agent.

skillaudit_gate

No parameter schema in public metadata yet.

skillaudit_scan

No parameter schema in public metadata yet.

skillaudit_scan_content

No parameter schema in public metadata yet.

skillaudit_reputation

No parameter schema in public metadata yet.

skillaudit_batch

No parameter schema in public metadata yet.

Sponsors

Promote your product hereReach 125k+ visitors monthly Promote your product hereReach 125k+ visitors monthly

Agent CaffeineSponsoredClose your lid, come back to finished work

SnugSponsoredThe clipboard manager for the AI era Promote your product hereReach 125k+ visitors monthly

WaxSponsoredBlock anything with supervision, without erasing your iPhone Promote your product hereReach 125k+ visitors monthly

knobsSponsoredSee your site on any phone, any day, in any language

Readme

🛡️ SkillAudit

The security layer for AI agent skills. Scan, gate, and enforce policy before your agent installs anything.

43 detection rules · 401 patterns · MCP + A2A coverage · Zero dependencies

# Gate check — should my agent install this?
npx skillaudit gate https://example.com/SKILL.md

# Full scan
npx skillaudit https://example.com/SKILL.md

# Scan MCP manifest for schema poisoning
npx skillaudit manifest tools.json

Why SkillAudit?

View the full README on GitHub

Details

Repository: github.com/megamind-0x/skillaudit
Website: skillaudit.vercel.app
Categories: AI & LLM Tools, Security & Pentesting, Data & Analytics
Transport: HTTP

Related AI & LLM Tools MCP servers

1

SecurityScansecurityscan-api/securityscan-apiScan GitHub-hosted AI skills for vulnerabilities: prompt injection, malware, OWASP LLM Top 10.0stars

2

Nexus Mcpnexus-api-lab/nexus-mcpJapanese LLM security — prompt injection detection (jpi-guard) + PII masking (PII Guard). Free.0stars

3

AgentWatchnicofains1/agentwatchMulti-agent observability: cascade failure detection, heartbeats, and forensic replay0stars

4

Roundtabledeadpixel/roundtable-dashboardMulti-model AI debates: GPT-4o, Claude, Gemini & 200+ models discuss, then synthesize insight.0stars

5

Mcp Bookmarkpree-dew/mcp-bookmarkMCP Server for adding bookmarks in openai RAG0stars

6

Psyseal scanpsyseal/psyseal-scanOffline check of your AI agent: heartbeat cost, plaintext keys, planted or bloated memory.0stars