new-issue

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

• Third-party content exposure detected (high risk: 0.90). The skill invokes GitHub CLI/API commands (e.g., gh issue list, gh search issues, gh issue view, gh api ...) to fetch issue titles, bodies, comments, and other repository content from GitHub — user-generated/untrusted third-party content that the agent reads and interprets for duplicate detection and issue drafting.