docs-seeker

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow and scripts explicitly fetch and ingest public documentation (llms.txt and linked URLs) from context7.com and other web sources (see SKILL.md Fetch step and scripts/fetch-docs.js which builds and https-get context7.com URLs, plus scripts/analyze-llms-txt.js and workflows/library-search.md/topic-search.md that instruct reading those URLs with WebFetch and deploying agents), so untrusted third‑party content is read and used to drive agent decisions and actions.