generate-github-issue

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly runs GitHub queries (e.g., "gh issue list --limit 10 ..." in Step 2 and the multi-strategy searches in Step 6) and reads existing issue titles/metadata from GitHub — user-generated, public/untrusted content that the agent is required to interpret and that can influence language choice, duplicate detection, and subsequent actions.