figma-to-angular

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted design metadata and reference code from Figma URLs using the get_design_context tool, creating a potential surface for instructions embedded in external designs. \n
  • Ingestion points: Design context (reference code, metadata, and screenshots) retrieved from figma.com via the Figma MCP server as described in Phase 1 of SKILL.md. \n
  • Boundary markers: The skill instructions do not prescribe the use of delimiters or specific "ignore embedded instructions" headers when handling the output from the Figma tool. \n
  • Capability inventory: The skill possesses capabilities to read project configuration files (tailwind.config) and write multiple new source files (.ts, .html, .spec.ts) to the local filesystem. \n
  • Sanitization: No explicit sanitization or validation of the structural reference code provided by the Figma tool is mentioned before it is utilized by the agent to generate production code.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 03:54 PM
Security Audit — agent-trust-hub — figma-to-angular