library-ebooks

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

• Third-party content exposure detected (high risk: 0.80). The skill fetches and parses HTML from configurable public library endpoints (via get_base_url()/fetch_url calling URLs like https://library-archive.org/search and /md5/), ingesting titles/metadata/download URLs from third‑party/public mirrors that the agent reads and interprets as part of its workflow.