canvas-design
Warn
Audited by Snyk on Aug 18, 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 specifies that the workflow uses “subtle input or instructions by the user” to generate the design philosophy (then expresses it visually), meaning outsider-authored free text supplied at run time is ingested by the required prompt/LLM steps.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata