{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreigmdyv6on5sincbf4dvgqogrwffb34rmkiwtsb74fzthhdn3ppdpy",
    "uri": "at://did:plc:25rdn5elo5izoxrmtis34zuk/app.bsky.feed.post/3mpuox2zuwpz2"
  },
  "coverImage": {
    "$type": "blob",
    "ref": {
      "$link": "bafkreihavsrc7fpvnkidzaalu3s4lotjsvz54abb5ind5cfirtvuheywgq"
    },
    "mimeType": "image/webp",
    "size": 77222
  },
  "path": "/dockfixlabs/agentguard-vs-semgrep-vs-codeql-100-percent-vs-0-percent-on-ai-agent-security-4iil",
  "publishedAt": "2026-07-05T02:56:40.000Z",
  "site": "https://dev.to",
  "tags": [
    "python",
    "security",
    "ai",
    "cybersecurity",
    "https://github.com/dockfixlabs/agentguard"
  ],
  "textContent": "I ran the same 39 AI agent security samples through three scanners: AgentGuard, Semgrep, and CodeQL.\n\n##  The Results\n\nScanner | Detection Rate | False Positives\n---|---|---\n**AgentGuard v0.6.4** | **100% (39/39)** | **0**\nSemgrep | 0% (0/39) | 0\nCodeQL | 0% (0/39) | 0\n\nZero. Semgrep and CodeQL detected nothing. They have zero rules for AI agent security.\n\nAgentGuard has 17 detection rules covering all 10 OWASP ASI categories plus 4 novel attack vectors: Memory Poisoning, Tool Output Trust, Action Chain Amplification, and Multi-Agent Collusion.\n\n##  Real World\n\nAgentGuard found 332 critical vulnerabilities across Microsoft AutoGen and LlamaIndex. Issues reported directly: autogen#7917, autogen#7918, llama_index#22245.\n\n##  Reproduce\n\n`\ngit clone https://github.com/dockfixlabs/agentguard-benchmark\ncd agentguard-benchmark\npip install dfx-agentguard\npython benchmark.py\n`\n\nGitHub: https://github.com/dockfixlabs/agentguard\nPyPI: pip install dfx-agentguard",
  "title": "AgentGuard vs Semgrep vs CodeQL: 100 Percent vs 0 Percent on AI Agent Security"
}