frontend-design
Warn
Audited by Snyk on Mar 15, 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 SKILL.md Figma Integration section instructs the agent to "Extract design context using
get_design_context" from Figma (MCP) and then map those variables to the token system and generate code, which clearly requires ingesting user-/third-party Figma files (untrusted content) that directly influence decisions and actions—creating a vector for indirect prompt injection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata