figma-context-reader

Pass

Audited by Gen Agent Trust Hub on Jul 29, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is designed for read-only operations on Figma design data. It includes explicit instructions for privacy compliance and evidence attribution.
  • [PROMPT_INJECTION]: The skill processes untrusted external data from Figma, such as node names and descriptions, which serves as a potential attack surface for indirect prompt injection. 1. Ingestion points: Figma URLs, node metadata, and screenshots as defined in SKILL.md. 2. Boundary markers: The skill mandates the use of evidence labels (metadata vs. inference) but does not explicitly instruct the agent to disregard instructions potentially embedded in Figma text fields. 3. Capability inventory: The skill is scoped to read-only operations via the figma:figma-use tool; no write or external network capabilities are requested. 4. Sanitization: No specific input sanitization or filtering is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 29, 2026, 07:30 AM
Security Audit — agent-trust-hub — figma-context-reader