cursor-build-figma
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to read and follow instructions from various untrusted or external data sources, including repository-local configuration files and Figma design metadata, which can be manipulated to influence the agent's behavior.
- Ingestion points: The skill explicitly reads from
AGENTS.md,.cursor/rules/,.cursor/skills/,CONTRIBUTING.md, and the Figma design context (get_design_context) as documented inreferences/design-system-discovery.mdandSKILL.md. - Boundary markers: There are no instructions provided to the agent to treat external repo files or Figma metadata as untrusted data or to ignore embedded instructions within them.
- Capability inventory: The skill has the capability to write files to the repository (implementation phase), write artifacts to
/tmp, and perform UI control via thecursor-control-uitool. - Sanitization: No sanitization, validation, or escaping of the content ingested from the repository files or Figma design context is specified before it is used to guide implementation logic.
Audit Metadata