fix-issue

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

• Third-party content exposure detected (high risk: 0.85). SKILL.md instructs using WebFetch and gh issue view --comments (and fetching sandbox/repo key files) to read full outsider-authored GitHub issue content and linked reproduction/code, which would be ingested as free-form text into the agent’s LLM context at runtime.