fix-security-issue

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

• Third-party content exposure detected (high risk: 0.90). The skill fetches and parses GitHub issue comments (via "gh issue view --json comments" and jq filtering for "security-review-agent"), which are user-generated/untrusted content, and explicitly extracts the remediation plan from those comments to drive code changes and next actions.