cc-figma-tokens
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local JSON token files, creating a theoretical attack surface for indirect prompt injection if the files are attacker-controlled.
- Ingestion points: Local JSON token files in
TOKENS_DIR(e.g.,primitive/color.tokens.json). - Boundary markers: No specific delimiters or safety instructions are defined to ignore embedded prompts within the token values.
- Capability inventory: The skill uses the
use_figmatool for API interaction and has file system read permissions. - Sanitization: No explicit sanitization or schema validation of the token values is mentioned, though the data is handled as structured JSON.
Audit Metadata