openclaw-coder-playbook
Warn
Audited by Snyk on Aug 19, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The runtime workflow reads outsider-authored free text from user-triggered channel/DM or thread messages (e.g., Step 1 in working-session.md calls
message action: "read"to ingest the thread starter/task authored by the chat participant).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata