research

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

• Third-party content exposure detected (high risk: 0.90). The skill's core workflow explicitly requires fetching and reading open web content and public GitHub repos (see SKILL.md "Tool Priority" listing gh api, web_search, tavily_extract_process and references/verification-patterns.md which instructs "WebFetch the URL" and to "Fetch the actual pages"), so untrusted third‑party pages and user-generated content are ingested and used to drive decisions.