prime-component-authoring
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run 'change-scoped repository checks' and 'verification commands' as part of the standard development and testing workflow.
- [INDIRECT_PROMPT_INJECTION]: The skill processes external data sources, including Figma design metadata and component implementation references from the Prime registry, which are used to generate React code. While this is an inherent surface for indirect prompt injection, it is within the standard functionality of a code-generation tool.
- Ingestion points: Figma design section data, Prime candidate component metadata, and implementation references.
- Boundary markers: No specific boundary markers or 'ignore' instructions for external data are defined in the SKILL.md.
- Capability inventory: The skill is capable of file writes (creating React components), modifying repository configuration (updating token sources), and executing shell commands (repository checks).
- Sanitization: The instructions do not specify sanitization or validation logic for the ingested design data before interpolation into the generation process.
Audit Metadata