extract-structure
Warn
Audited by Snyk on May 18, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The skill explicitly ingests user-generated design data from {cachePath}/{componentSlug}-_base.json (produced by the uSpec Figma plugin) and may also perform optional read-only figma_execute / use_figma delta calls against live Figma files (Step 3-delta), both of which are untrusted third-party content that the agent reads and uses to drive interpretation and downstream decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata