attention-frontier
Warn
Audited by Snyk on Nov 1, 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 workflow reads agent conversations and thread content via tool calls (
list_threads,read_thread,wait_threads), which are user-facing chat transcripts containing outsider-authored free text.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata