model-evaluator-validator
Warn
Audited by Snyk on Jul 12, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). SKILL.md describes receiving an outsider-authored raw output file from
data-scientist-analystand then computing metrics/tests from that file, which would be ingested as readable text/CSV content into the agent’s runtime context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata