figma-spec
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill defines a specialized set of operations for Figma documents within the platform's API constraints. It explicitly enforces permission checks using a
whoamicall and mandates that portable references (URLs) be used instead of local machine paths. - [INDIRECT_PROMPT_INJECTION]: The skill processes Markdown content from external Figma files, which represents an attack surface for indirect prompt injection.
- Ingestion points: Data enters the agent context via
figma.spec.getContentas described inSKILL.md. - Boundary markers: No specific delimiters or instructions to ignore instructions embedded in the Markdown are provided.
- Capability inventory: The agent can modify Figma nodes (
figma.spec.setContent,figma.spec.editContent) and create comments (figma.spec.comments.create). - Sanitization: The skill does not describe specific sanitization or filtering of the Markdown content retrieved from Figma.
Audit Metadata