c-replicate
Warn
Audited by Snyk on May 5, 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's sync-models.sh automatically fetches public model metadata from the Replicate API (https://api.replicate.com/v1/models) into models.jsonl, and SKILL.md shows that the agent reads/searches that file to pick and invoke models—meaning untrusted, user-provided model names/descriptions on replicate.com can influence which tools/actions the agent runs.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata