security-incident-response

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill's workflow (SKILL.md "Research the incident" and related steps) explicitly instructs the agent to fetch and read open/public third‑party sources (NVD/CVE, GitHub Security Advisories, vendor advisories, GitHub repos) and even to git clone/run scanners from public GitHub, so it ingests untrusted external content that can materially influence decisions and tool actions.