openclaw-secret-scanning-maintainer

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

• Third-party content exposure detected (high risk: 0.95). Outsider-authored free text from GitHub issue/PR bodies and comments (e.g., comment.body, issue.body, pr.body, and DiscussionComment.body) is fetched at runtime via gh api / ghGraphQL in fetch-content, written to a temp file, and then the agent reads that file for semantic redaction (Step 2), so the LLM context can include untrusted outsider text.