review-changes

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

• Third-party content exposure detected (high risk: 0.70). The skill's SKILL.md explicitly instructs fetching PR content via "PR number or URL" and running gh pr view <n> / gh pr diff <n>, which ingests user-generated PR titles/bodies/diffs from third-party GitHub repos that the agent reads as part of its workflow and can influence review decisions.