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 scripts and workflows (notably scripts/fetch-docs.js and SKILL.md/workflows/*.md) explicitly fetch and ingest llms.txt and other documentation from public sites like context7.com (with fallbacks to web search results and GitHub repositories via repo-analysis), and those fetched pages are read/processed and used to decide agent deployment and next actions—exposing the agent to untrusted third‑party content that could carry indirect prompt injections.