debug-like-expert

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs the agent to perform web searches and consult external MCP/GitHub/Stack Overflow sources as part of "Gather External Knowledge" (see "C. Gather External Knowledge" and "when-to-research.md"), which requires fetching and reading untrusted public third‑party content.