figma-handoff-gate

Pass

Audited by Gen Agent Trust Hub on Oct 8, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from Figma text nodes, frame names, and descriptions, creating a surface for embedded instructions to influence the agent.
  • Ingestion points: SKILL.md (Checks 11 and 16) reads content from n.characters, n.name, and n.description across various Figma nodes.
  • Boundary markers: Absent; the skill does not implement delimiters or warnings to ignore potentially malicious instructions inside the ingested data.
  • Capability inventory: The agent uses figma_execute for multiple auditing tasks and has access to figma_capture_screenshot for visual proof.
  • Sanitization: Absent; external content from the Figma document is used directly in logic (regex, list matching) without escaping or validation.
  • [DYNAMIC_EXECUTION]: The skill requires the agent to generate and execute code at runtime to resolve audit findings.
  • Evidence: The "Apply-fix commands" section in SKILL.md instructs the agent to dynamically "write that code for the approved fix" and execute it via the figma_execute tool.
  • [COMMAND_EXECUTION]: The skill provides predefined JavaScript snippets to be executed against the Figma Plugin API.
  • Evidence: Several checks (e.g., Check 11, 15, 16, and 17b) provide JavaScript blocks intended to be run through the figma_execute tool, allowing the agent to read and modify the active Figma document environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 8, 2026, 08:05 AM