tao-run-deft-aoi
Warn
Audited by Snyk on Sep 21, 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 and parses user-supplied evaluation manifests, test CSVs, and data rows from disk (
testing_set.csv,training_set.csv,mining_pool.csv), which could contain untrusted outsider-authored text when supplied by an external user.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata