AgentSec Audit

AgentSec Audit launched as an automated security scanner, policy linter, and compliance certification tool for autonomous AI agents, tool configurations, and Model Context Protocol (MCP) servers. The tool enforces the OWASP Top 10 for Agentic Applications (2026 ASI01–ASI10) and targets ISO 42001 and SOC 2 Type II processing integrity audits, detecting arbitrary shell/eval execution, goal hijacking vectors, unbounded delegation depth, and unsanitized memory write loops. AgentSec Audit exposes an audit_agent_config interface over stdio JSON-RPC for Hermes Desktop, Claude Code, and Codex, and ships with GitHub Actions CI/CD gating via hicklax13/agentsec-audit@v1.

Automated security scanning, policy linting, and compliance certification for autonomous AI agents, tool configurations, and Model Context Protocol MCP servers. Built for the OWASP Top 10 for Agentic Applications 2026 ASI01–ASI10 and ISO 42001 / SOC 2 Type II processing integrity audits. - Deterministic Static AST & Schema Linter: Scans system prompts, function calling schemas, and MCP tool declarations. - OWASP ASI-10 Rule Enforcement: Detects arbitrary shell/eval execution, goal hijacking vectors, unbounded delegation depth, and unsanitized memory write loops. - Native MCP Interface: Exposes audit agent config over stdio JSON-RPC so Hermes Desktop, Claude Code, and Codex can audit agents natively. - Turnkey CI/CD: Ready for GitHub Actions with automated PR pass/fail gating. git clone https://github.com/hicklax13/agentsec-audit.git cd agentsec-audit pip install -r requirements.txt python -m src.cli scan ./sample agent.json --format html --out report.html Add this to your repository workflow: name: AgentSec Compliance Check on: push, pull request jobs: audit: runs-on: ubuntu-latest steps: - uses: actions/checkout@v4 - uses: hicklax13/agentsec-audit@v1 with: config-path: "agent.json" fail-on-violation: "true"