ux-writing
Warn
Audited by Snyk on Feb 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill's Figma integration (see docs/claude-figma-integration.md and docs/codex-figma-integration.md) explicitly tells users to paste public or shared Figma links so Claude/Codex will access frames and extract text from those third-party, user-authored designs, which is untrusted content the agent will read and interpret.
Audit Metadata