generate-issue

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly reads user-generated GitHub issues via gh issue list (Step 2 language detection) and performs multi-strategy searches of repository issues (gh issue list in Step 6) — untrusted third-party content that the agent must interpret and that can change its decisions about duplicates, language, labels, and whether/how to create or comment on issues.