audit-library-health

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

• Third-party content exposure detected (high risk: 0.70). The skill's "check" step explicitly makes network requests to verify upstream sources (e.g., public/upstream repositories) as noted in the Gotchas, so the agent fetches and interprets third‑party repository content to drive update/curation decisions, which could enable indirect prompt injection.