figma
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external Figma documents which could be manipulated by third parties to include malicious instructions or text patterns.
- Ingestion points: Reads node names, component metadata, and variables through the Figma REST API as seen in SKILL.md and gpt.md.
- Boundary markers: The instructions do not specify any delimiters or safety warnings to ignore embedded text within the processed Figma data.
- Capability inventory: The skill performs network operations to the Figma API and provides templates for generating TypeScript plugin code.
- Sanitization: There is no description of input validation or sanitization for strings or metadata retrieved from the Figma API before they are processed by the agent.
Audit Metadata