by HeadyZhang · MCP Server · ★ 133
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. Prompt injection rewrites agent intent through user-controlled context Unsafe tool inputs can reach / and become command execution MCP configuration mistakes can leak credentials and expand access unintentionally If your team ships agent features, owns CI security gates, or operates MCP servers and tool integrations, this
| Stars | 133 |
| Forks | 12 |
| Language | Python |
| Category | MCP Server |
| License | MIT |
| Quality Score | 65.1/100 |
| Last Updated | 2026-03-28 |
| Created | 2026-02-03 |
| Platforms | cli, mcp, python |
| Est. Tokens | ~104k |
These tools work well together with agent-audit for enhanced workflows:
Explore other popular mcp server tools:
agent-audit is Static security scanner for LLM agents — prompt injection, MCP config auditing, taint analysis. 49 rules mapped to OWASP Agentic Top 10 (2026). Works with LangChain, CrewAI, AutoGen.. It is categorized as a MCP Server with 133 GitHub stars.
agent-audit is primarily written in Python. It covers topics such as ai-agent, ai-security, ai-security-tool.
You can find installation instructions and usage details in the agent-audit GitHub repository at github.com/HeadyZhang/agent-audit. The project has 133 stars and 12 forks, indicating an active community.
agent-audit is released under the MIT license, making it free to use and modify according to the license terms.