gh-pr-comments-all

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

• Third-party content exposure detected (high risk: 0.95). The skill calls GitHub REST endpoints at runtime (/pulls/{n}/comments, /pulls/{n}/reviews, and /issues/{n}/comments) and ingests their returned JSON fields (including body free text) into the LLM context via the skill’s output/processing pipeline, which is outsider-authored PR comment/review text.