github

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

• Third-party content exposure detected (high risk: 0.85). The skill uses gh pr view, gh issue list, gh run view, and gh api ... to fetch PR/issue/run content from GitHub at runtime; that content is authored by other users (e.g., PR bodies, issue text, comments, CI logs) and is ingested into the agent’s LLM context via the command output.