maintainer-review

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

• Third-party content exposure detected (high risk: 0.85). The workflow ingests outsider-authored free text from GitHub issue/PR bodies and comments at runtime (e.g., “read the full report, comments, reproduction…” and “inspect… review discussion”), which can contain indirect prompt-injection content that is then placed into the agent’s LLM context.