debug-like-expert

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

• Third-party content exposure detected (high risk: 0.80). This skill's SKILL.md (quick_start → "C. Gather External Knowledge (when needed)") and references/when-to-research.md explicitly instruct the agent to use web search, GitHub issues and other external docs—i.e., fetch and read public, user-generated web content—which the agent is expected to interpret and use to guide debugging decisions.