gauntlet-loop
Warn
Audited by Snyk on Sep 12, 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 consumes outsider-authored free text through
gauntlet observe import,langsmith,atof, andotel(as well as handling untrusted trace and observation payloads), which ingest unstructured external data into the runtime.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata