cd /news/ai-safety/agentsec-audit · home topics ai-safety article
[ARTICLE · art-134955] src=github.com ↗ pub= topic=ai-safety verified=true sentiment=· neutral

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.

read1 min views2 publishedSep 20, 2026
AgentSec Audit
Image: Michielbdejong (auto-discovered)

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: Exposesaudit_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"
── more in #ai-safety 4 stories · sorted by recency
── more on @agentsec audit 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/agentsec-audit] indexed:0 read:1min 2026-09-20 ·