{
  "entry": {
    "kind": "vuln",
    "slug": "a-hole-in-every-one-one-malicious-agent-skill-defeats-all-eight-open",
    "name": "a-hole-in-every-one-one-malicious-agent-skill-defeats-all-eight-open",
    "vendor": "One Malicious Agent Skill Defeats All Eight Open-Source Skil",
    "description": "Adversa AI built a single malicious agent skill and ran it past all eight open-source AI skill scanners currently available. Every one passed it. The finding matters because skill scanning is the control most teams rely on when they let developers install community skills, so a uniform bypass means that control is providing assurance it cannot actually deliver.",
    "website": "https://adversa.ai/blog/agent-skill-scanners-bypass-eight-tested/",
    "repository": null,
    "documentationUrl": null,
    "license": null,
    "version": null,
    "trustLevel": "advisory",
    "capabilities": [],
    "packaging": null,
    "configFiles": null,
    "category": "agent",
    "updatedAt": "2026-07-30",
    "risk": {
      "score": 75,
      "band": "high",
      "signals": [],
      "dangerousCombos": []
    },
    "dangerousCombos": [],
    "vuln": {
      "id": "a-hole-in-every-one-one-malicious-agent-skill-defeats-all-eight-open",
      "aliases": [
        "ti-064"
      ],
      "title": "A Hole in Every One: One Malicious Agent Skill Defeats All Eight Open-Source Skill Scanners",
      "summary": "Adversa AI built a single malicious agent skill and ran it past all eight open-source AI skill scanners currently available. Every one passed it. The finding matters because skill scanning is the control most teams rely on when they let developers install community skills, so a uniform bypass means that control is providing assurance it cannot actually deliver.",
      "severity": "high",
      "cvss": {
        "score": null,
        "vector": null,
        "version": null
      },
      "cwe": [],
      "attackType": [
        "Prompt injection"
      ],
      "componentType": "agent",
      "component": {
        "name": "One Malicious Agent Skill Defeats All Eight Open-Source Skil",
        "vendor": null,
        "package": null,
        "ecosystem": null,
        "catalogSlug": null
      },
      "affected": [
        {
          "range": null,
          "fixed": null
        }
      ],
      "exploited": false,
      "exploitPublic": false,
      "publishedAt": "2026-07-30",
      "modifiedAt": "2026-07-30",
      "lastVerified": "2026-11-01",
      "references": [
        {
          "type": "article",
          "url": "https://adversa.ai/blog/agent-skill-scanners-bypass-eight-tested/"
        }
      ],
      "mitigation": "Do not treat a clean skill-scanner result as approval. Govern skills by provenance instead: allowlist the publishers you trust, inventory every skill actually installed across the fleet, and alert on new skills appearing on a device rather than trying to detect malice in their content.",
      "detectedByAnomity": true
    }
  }
}