repo-issue-triage

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

• Third-party content exposure detected (high risk: 0.95). This skill’s required workflow explicitly says to “Read the full issue or request, including prior notes” (outsider-authored issue/comment text from GitHub/trackers) and then use that content to produce recommendations, so the LLM context will include free-form outsider text at runtime.