figma
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of purely instructional markdown content. No executable scripts, network exfiltration, or hardcoded credentials were found.
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a workflow for ingesting and processing data from external Figma files, which serves as a potential surface for indirect prompt injection. This is evaluated as safe as it is fundamental to the skill's purpose and lacks autonomous dangerous capabilities.
- Ingestion points: Figma file content (nodes, layers, components, variables) referenced in SKILL.md.
- Boundary markers: None specified; the agent is instructed to read raw node data.
- Capability inventory: Interaction with Toolcraft schema controls and product renderer output as described in SKILL.md.
- Sanitization: No explicit sanitization of Figma metadata or node content is mentioned.
Audit Metadata