figma-generate-library
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data by scanning React component files in the
src/components/andgenerated/directories to identify props, variants, and Tailwind classes. - Ingestion points: The agent reads local source code files (SKILL.md, Step 2).
- Boundary markers: No specific delimiters or instructions to ignore embedded content within the source files are defined.
- Capability inventory: The skill uses
figma_batch_create_variables,use_figma, andadd_code_connect_mapto modify Figma design files and project configuration (SKILL.md, Steps 3, 4, and 6). - Sanitization: No explicit sanitization or validation of the ingested code content is described prior to property mapping.
- [COMMAND_EXECUTION]: The skill utilizes several domain-specific CLI tools and tool calls such as
memi connect,get_code_connect_map, andmemi spec. These appear to be legitimate project-specific tools provided by the author to maintain design-code parity.
Audit Metadata