figma-generate-library

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill is designed to generate and execute JavaScript code within the Figma Plugin API environment via the use_figma tool. It orchestrates complex multi-step workflows involving 20–100+ tool calls to build design components, variables, and pages.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as its primary function (Phase 0: Discovery) involves reading and parsing untrusted data from the user's codebase.
  • Ingestion points: The agent is instructed to read *.tokens.json, *.css, tailwind.config.js, and theme files in references/discovery-phase.md.
  • Capability inventory: The skill can modify the Figma document, read/write Figma plugin data, and maintain a state ledger in a local temporary file (/tmp/dsb-state-{RUN_ID}.json).
  • Boundary markers: The instructions do not specify the use of XML delimiters or 'ignore' instructions when processing the content of the analyzed codebase files.
  • Sanitization: There is no explicit requirement for the agent to sanitize or validate the content extracted from the codebase before interpolating it into Figma mutation scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 09:08 AM
Security Audit — agent-trust-hub — figma-generate-library