team-test

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

• Third-party content exposure detected (high risk: 0.90). The skill's Step 0 scope detection explicitly runs commands like gh pr view <N> --json title,body,files and gh issue view <N> --json title,body,comments, meaning the agent fetches and ingests user-generated PR/issue content from third-party GitHub sources and uses it as part of analysis and to seed subagents.