fix

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

• Third-party content exposure detected (medium risk: 0.65). SKILL.md instructs collecting/creating bug context and diagnostic logs that include user-provided free-form bug descriptions and error messages (User Input $ARGUMENTS, later “User-Provided Information” fields), which are then used by the agent’s LLM for diagnosis/presentation, creating an indirect prompt-injection path from outsider-authored user text into LLM context.