firstrun
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DYNAMIC_EXECUTION]: The skill utilizes tools such as
figma_executeanduse_figmato run a predefined Javascript snippet within the Figma environment for detecting font families from text nodes. This is a standard use of the Figma MCP to achieve the skill's stated goals. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied Figma URLs to extract file keys. This data ingestion is used to scope subsequent search and retrieval operations within Figma. The risk is minimized as the skill only searches for specific template names and extracts component keys.
- [SAFE]: The skill manages a local configuration file,
uspecs.config.json, by reading existing values and appending new template-specific metadata. The inclusion of hardcoded component keys for specific organizational use cases (e.g., Uber) is a documented feature and does not present a security risk.
Audit Metadata