Replicate Automation
Warn
Audited by Snyk on Mar 29, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). This skill explicitly fetches public Replicate model READMEs and model schemas (via REPLICATE_MODELS_README_GET and REPLICATE_MODELS_GET) and instructs the agent to read those user-provided/open public model documents before constructing inputs, so untrusted third-party content can influence actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata