gh-issue-resolver

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly fetches GitHub issue comments using "gh issue view --json ... comments" and treats the most recent comment containing the marker (user-generated content on a public GitHub issue) as the authoritative implementation plan, so untrusted third-party content can directly drive code changes and workflow decisions.