data-flywheel
Warn
Audited by Snyk on May 13, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill exposes untrusted, user-provided content via the POST /ingest endpoint (stored in the training_data table) which the training worker then reads in train_and_publish to retrain models, so arbitrary third‑party inputs can materially influence model behavior.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata