web-search-researcher

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

• Third-party content exposure detected (high risk: 1.00). The skill's core workflow explicitly instructs the agent to perform web searches and "Fetch — Retrieve content from authoritative sources" (SKILL.md core process) and progressive.md/strategies.md instruct fetching pages from public sites like Stack Overflow, blogs, and GitHub, so the agent will read and act on untrusted third‑party web content.