review-issue

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md Step 1 explicitly instructs the agent to fetch GitHub issue title/body/comments and linked PRs via the gh CLI (e.g., "gh issue view {ISSUE_NUMBER} --json title,body,comments" and related gh pr commands), which are user-generated, potentially public third-party contents that the agent must read and use to decide actions such as closing issues.