agent-config-audit
Audit AI agent configuration files for security risks.
What it is
One command reads the files that launch and instruct a coding agent (.claude/settings*.json, .mcp.json, claude_desktop_config.json, .cursor/ rules and MCP config, CLAUDE.md and the files it imports, AGENTS.md, plugin manifests, hooks, skills) and reports pre-approved dangerous commands, bypassed permission prompts, rules Claude Code silently skips, secrets next to server definitions, unpinned MCP servers, hooks that phone home and prompt-injection text. Output as a table, JSON, Markdown or SARIF for GitHub code scanning. Read-only, standard library only, no network.
Who it is for: developers who open other people's repositories with Claude Code, Cursor or another agent, and teams who review .claude/ and .mcp.json changes in pull requests.
Install
pipx install git+https://github.com/basitalisandhu/agent-config-audit
cd your-project
agent-config-audit --fail-on high
From the README; see the full README for every option.
Links
Releases
More in Security tooling
- agent-off-switch: Find every AI agent identity in Microsoft 365, AWS and GitHub, see what it can reach, and switch it off. Offline on saved exports.
- skill-scan-gate: CI gate for Claude Code skills and plugins, with SARIF output. GitHub Action and CLI.
- agent-threat-model: Threat modeling for AI agents: describe the system in YAML, get a STRIDE and OWASP Agentic threat model.
- agentic-semgrep-rules: Semgrep rules for AI agent code in Python, TypeScript and JavaScript.
- security-actions: GitHub Actions for AI agent and supply chain security checks.
- cc-hooks: Typed Python SDK and offline test runner for Claude Code hooks.
- cc-plugin-lock: Lock file for Claude Code plugins: pins plugins and skills to content hashes and verifies them before load.
- claude-perm-sim: Claude Code permission rule simulator: shows which rule decides a tool call and where a rule set is permissive.
- llms-txt-gen: Generate llms.txt for any docs site or repository.
- scp-guardrails: Build AWS service control policies from a short spec and lint them for lockouts and statements that deny nothing.
- spotlighting: Spotlighting for prompt injection defence in Python: mark untrusted text before it reaches a model.
- llm-agent-control-plane: Deterministic policy enforcement for LLM agents.
Topics: agent-security, ai-agents, ai-security, claude-code, claude-md, cli, configuration-audit, cursor, devsecops, github-actions, hacktoberfest, llm-security, mcp, pre-commit, prompt-injection, python, sarif, secrets-detection, security-automation, security-tools