atlas-cloud
Warn
Audited by Snyk on Aug 14, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). SKILL.md describes a workflow that accepts user-supplied free text in
tool.execute({ "prompt": "..." })for Atlas image/video generation, meaning the runtime ingests outsider-authored prompt text before selecting and calling an exact Atlas model.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata