figma-audit-accessibility
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill ingests user-controlled component descriptions from the Figma environment and returns them to the agent context, creating a potential indirect prompt injection surface.
- Ingestion points: Component descriptions are read in
scripts/audit-accessibility.js. - Boundary markers: The data is provided to the agent in a standard JSON format without explicit delimiters or instructions to ignore instructions embedded in the description.
- Capability inventory: While this skill's scripts use the Figma Plugin API in a read-only manner, the agent possessing this data may have access to other tools with broader system capabilities.
- Sanitization: The description string is truncated to a maximum of 200 characters before being processed.
Audit Metadata