workflow-from-chats
Warn
Audited by Snyk on Aug 22, 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 required runtime workflow explicitly scans and reads parent and relevant subagent chat transcripts from Codex, Pi, and Claude Code at runtime to extract “explicit preferences, corrections, and workflow markers,” which can include outsider-authored free text from those chat sessions.]
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata