maintainer-sweep

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

• Third-party content exposure detected (high risk: 0.85). At runtime the workflow runs gh issue view <n> / gh pr view <n> and reads issue/PR bodies and comments, which are outsider-authored free text from GitHub users (not the operating user), then feeds that text into the agent’s LLM context for analysis and follow-up.