gh-credit-harvest

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

• Third-party content exposure detected (high risk: 0.95). The skill’s runtime workflow ingests outsider-authored free text from the community PR via gh pr view <N> ... and gh pr diff <N> ... (PR title/comments/diff content authored by someone other than the operating user), which is then used as LLM context for review/decision-making.