sync-figma-token
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external design tokens from JSON files and Figma variables, which serves as an ingestion point for untrusted data.
- Ingestion points: Reads from
tokens.json, Style Dictionary files, and Figma variable collections via thefigmaMCP server. - Boundary markers: The instructions do not define specific delimiters or boundary markers for the data being synchronized.
- Capability inventory: The skill utilizes the
use_figmatool, which has the capability to modify Figma files and variables. - Sanitization: No explicit sanitization or validation of string values (which might contain instructions) is specified, though numeric tolerance is applied for colors and floats.
- Mitigation: The skill implements a robust safety rule requiring a mandatory dry-run followed by an explicit human approval gate (
Apply these changes? (yes/no)) before any write operations are executed, effectively preventing automated exploitation.
Audit Metadata