codebase-onboarding

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

• Third-party content exposure detected (medium risk: 0.65). The required workflow reads local repository intent/history/issue/PR text (e.g., “open issues and PRs” via gh issue list / gh pr list), which can include outsider-authored free-form content, and that text can be ingested into the agent’s LLM context as part of the reconnaissance report.