figma-api
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides a large surface area for processing untrusted data retrieved via the Figma API, which could be used as a vector for indirect prompt injection.
- Ingestion points: Multiple operations listed in the
references/operations/directory (e.g.,getFile.md,getComments.md,getActivityLogs.md) ingest user-generated content from external Figma accounts into the agent's context. - Boundary markers: There are no explicit instructions or boundary markers defined in the documentation to ensure the agent ignores instructions potentially embedded in the Figma resource data (e.g., within file comments or layer names).
- Capability inventory: The skill includes powerful write operations like
postWebhook(references/operations/postWebhook.md),postVariables(references/operations/postVariables.md), andpostComment(references/operations/postComment.md) that could be triggered by instructions found in ingested data. - Sanitization: The documentation does not specify any sanitization or validation logic to be applied to the data retrieved from the API before it is processed by the agent.
Audit Metadata