training-check
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: 1.00). The skill explicitly fetches and reads user-run metrics from the third-party service Weights & Biases (via wandb.Api().run("//<run_id>").history()) and uses those untrusted, user-generated metrics to make automated Stop/Continue/Wait decisions in the SKILL.md workflow.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata