ylf-figma
Pass
Audited by Gen Agent Trust Hub on Oct 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted design data from Figma which could serve as a vector for malicious instructions.
- Ingestion points:
get_design_context,get_metadata, and image/SVG assets from Figma MCP tools inSKILL.md. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are defined for the processed design data.
- Capability inventory: The skill modifies repository code, saves external assets to the file system, and executes shell commands for application testing and Playwright automation.
- Sanitization: No sanitization or validation of the input design context is specified before it is used in code generation or verification steps.
Audit Metadata