skills/vm0-ai/vm0-skills/figma/Gen Agent Trust Hub

figma

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes bash -c and curl to perform API requests. The use of string interpolation for the <file-key> placeholder within a shell command introduces a potential command injection vulnerability if the agent parses a malicious Figma URL containing shell metacharacters (e.g., single quotes or semicolons).
  • [PROMPT_INJECTION]: The skill processes untrusted external data from Figma, creating an indirect prompt injection surface.
  • Ingestion points: Figma URLs and file content (including comments and component descriptions) retrieved from api.figma.com (SKILL.md).
  • Boundary markers: No explicit boundary markers or instructions to ignore embedded instructions are used when displaying or processing the fetched content.
  • Capability inventory: The skill has the capability to execute shell commands via bash and make network requests via curl (SKILL.md).
  • Sanitization: No sanitization or validation of the input data or the retrieved API content is performed before use in commands or prompts.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 07:15 AM