agent-audit: Static security scanner for LLM agents — prompt injection, MCP config auditing, taint analysis

by HeadyZhang · MCP Server · ★ 245

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

How to install agent-audit

pip install agent-audit
npx clawhub@latest install agent-audit-scanner

Taken from the project's README on GitHub.

Security audit verdict: SAFE · quality 75/100

Flagged: spawns subprocesses. Scanned against 44 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours.

The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.

ai-agentai-securityai-security-toolclicrewailangchainlangchain-security-llm-safetyllm-securitymcp

Quick Facts

Stars245
Forks30
LanguagePython
CategoryMCP Server
LicenseMIT
Quality Score75/100
Open Issues6
Last Updated2026-09-13
Created2026-02-03
Platformscli, mcp, python
Est. Tokens~17k

About agent-audit

Agent Audit Find security vulnerabilities in your AI agent code before they reach production. []() Why Agent Security Fails in Production AI agents are not just chatbots. They execute code, call tools, and touch real systems, so one unsafe input path can become a production incident.

Compatible Skills

These tools work well together with agent-audit for enhanced workflows:

  • openclaw-skills-security — semantic(0.38)+complementary+rare_topics+same_lang+similar_pop+shared_platform (72%)
  • Multi-Agent-AI-Travel-Advisor — semantic(0.17)+complementary+shared_fw(crewai,langchain)+rare_topics+same_lang+similar_pop+shared_platform (71%)
  • Tiger — semantic(0.18)+complementary+shared_fw(autogen,crewai,langchain)+same_lang+similar_pop+shared_platform (71%)
  • Agent-Wiz — semantic(0.15)+complementary+shared_fw(autogen,crewai)+rare_topics+same_lang+similar_pop+shared_platform (71%)
  • whistleblower — semantic(0.40)+complementary+rare_topics+same_lang+similar_pop+shared_platform (68%)

agent-audit alternative? Top 6 similar tools

Looking for a agent-audit alternative? If you're comparing agent-audit with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • agentseal by AgentSeal · ⭐ 156

    Security toolkit for AI agents. Scan your machine for dangerous skills and MCP configs, monitor for supply cha

  • medusa by Pantheon-Security · ⭐ 1.0k

    AI-first security scanner. NEW in v2026.7: Claude Code compromise detection — vet .claude/ hooks, permissions

  • agent-security-scanner-mcp by sinewaveai · ⭐ 123

    Security scanner MCP server for AI coding agents. Prompt injection firewall, package hallucination detection (

  • agentic-radar by splx-ai · ⭐ 1.1k

    A security scanner for your LLM agentic workflows

  • api by vulnersCom · ⭐ 377

    Official Python SDK for the Vulners vulnerability-intelligence API — search CVEs, exploits and advisories (CVS

  • opentaint by seqra · ⭐ 175

    The open source taint analysis engine for the AI era. A formal dataflow analysis tool you can customize and se

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Python Agent Tools

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 44 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse MCP Server tools