figma-canon

Pass

Audited by Gen Agent Trust Hub on Oct 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONCREDENTIALS_UNSAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides detailed instructions for the agent to execute shell commands, including npm install, node, python3, kill, lsof, and curl. Notably, references/field-notes.md describes a recovery mechanism that involves spawning a background daemon using nohup node <mcp-direct>/daemon.mjs & to bypass connectivity issues.
  • [DYNAMIC_EXECUTION]: The skill's primary functionality relies on generating and executing JavaScript code within the Figma plugin sandbox using the figma_execute tool. This allows the agent to perform complex design and data operations, but represents a significant capability that must be handled carefully.
  • [EXTERNAL_DOWNLOADS]: The skill directs the agent to download and install Node.js packages like @figma/code-connect and fetch assets from external sources such as itunes.apple.com for icon retrieval. These sources are generally well-known, but represents the ingestion of external code and data.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external data from Figma files (layer names, text content, annotations), which the skill explicitly identifies in references/security-canon.md as untrusted sources that could potentially harbor prompt injection attacks.
  • [CREDENTIALS_UNSAFE]: The skill mentions the use of the FIGMA_ACCESS_TOKEN environment variable for authentication. It provides safety instructions for handling this token, such as not printing it to logs or committing it to repositories, but acknowledges the presence of sensitive credentials in the environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 8, 2026, 08:06 AM