sweep-all
Warn
Audited by Snyk on Jul 30, 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 ingests first-party user/attacker-authored conversation text by dispatching conversation-inheriting fork subagents (step 1 canary + per-member audit forks) that read the live transcript to generate audit ledgers and then drive corrective writes.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata