figma-generate-diagram

Pass

Audited by Gen Agent Trust Hub on Jul 8, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • Indirect Prompt Injection Surface: The skill is designed to ingest data from external sources, such as source code, documentation, and other MCP servers, to provide context for diagram generation. This is a standard operational surface for AI agents, but it is noted as it involves processing untrusted content.
  • Ingestion points: The instructions in SKILL.md (Step 4) direct the agent to read from source code files, user-provided documents (PRDs, specs), and other connected tools.
  • Boundary markers: The skill does not currently specify the use of delimiters or specific instructions to ignore embedded prompts within the gathered context.
  • Capability inventory: The agent uses tools including generate_diagram, use_figma, and filesystem read operations to perform its tasks.
  • Sanitization: There are no explicit sanitization or validation steps mentioned for the content retrieved from external sources before it is formatted into Mermaid syntax.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 8, 2026, 12:29 PM
Security Audit — agent-trust-hub — figma-generate-diagram