triage

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

• Third-party content exposure detected (high risk: 0.85). Outsider free text is ingested via gh issue view <n> --json comments --jq '.comments[] | select(.author.login=="bitbonsai") | .body' (and also issue/PR bodies/logs from gh issue list / gh run view --log-failed), which are third-party-authored comment bodies and CI log text read at runtime into the agent context.