production-audit

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

• Third-party content exposure detected (low risk: 0.10). SKILL.md specifies an audit built from local and user-authorized evidence with no unpinned remote code or third-party data sharing, and the workflow only optionally checks a user-supplied deployed URL (via browser/HTTP checks) after establishing the release surface—so it does not describe ingesting outsider-authored free text from attacker-controlled queues/feeds without prior selection/authorization.