figma-generate-library
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it is designed to ingest and process untrusted data from local codebase files to influence Figma asset generation.\n
- Ingestion points: discovery-phase.md specifies the ingestion of various codebase files, including CSS, JSON, and JavaScript/TypeScript configuration files (e.g., tailwind.config.js, *.tokens.json).\n
- Boundary markers: The skill does not instruct the agent to use delimiters or ignore embedded instructions within these source files.\n
- Capability inventory: The skill uses the use_figma tool to perform significant mutations on Figma documents, such as creating pages, variables, and component sets.\n
- Sanitization: The skill lacks explicit sanitization or validation of the extracted content before using it to generate tool parameters.\n- [DYNAMIC_EXECUTION]: The skill assembles JavaScript code at runtime to be executed within the Figma plugin environment via the use_figma tool.\n
- Evidence: SKILL.md and various references provide instructions for embedding helper scripts from the scripts/ directory into tool calls. This is assessed as low severity because the scripts are included within the skill package and facilitate its primary intended function.
Audit Metadata