openclaw-pr-maintainer

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

• Third-party content exposure detected (high risk: 0.85). The skill is for maintainer-facing GitHub workflow, and at runtime it will typically ingest outsider-authored GitHub issue/PR text (e.g., issue bodies, PR descriptions, and especially issue/PR comments) via GitHub API/CLI search results into the agent’s LLM context for triage/labeling decisions.