awesome-web-agents-pr-review

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

• Third-party content exposure detected (high risk: 1.00). The skill's workflow explicitly instructs the agent to fetch and read GitHub pull request data and diffs (via gh pr view, gh pr diff, and fetching pull branches) — public, user-generated content — and to interpret that content to make review/merge decisions, which enables indirect prompt injection.