skill-review

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

• Third-party content exposure detected (high risk: 0.90). The skill's required review workflow (SKILL.md step 3 and references/checks-references.md Check 1/Check 3 and the URL Reachability steps) explicitly instructs the agent to use WebFetch to fetch and verify every URL found in skill/reference files, meaning arbitrary public third‑party pages will be ingested and used to decide pass/fail outcomes—exposing the agent to untrusted external content that can materially influence behavior.