Back to skill

Security audit

figma-to-mobile

Security checks across malware telemetry and agentic risk

Overview

This skill is a Figma-to-mobile-code helper whose network use, local project scanning, and feedback logging are mostly disclosed and tied to its purpose, but users should approve scans and logs deliberately.

Install only if you are comfortable giving the skill a Figma token through the environment and letting it read the selected mobile project when you approve a scan. Do not paste the token into chat, review any requested scan path before approving, and avoid logging feedback snippets that contain sensitive product details unless you are comfortable storing them locally.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (3)

Natural-Language Policy Violations

Medium
Confidence
79% confidence
Finding
The skill hardcodes a Chinese-language consent prompt for local project scanning instead of matching the user's language or offering a choice. This can weaken informed consent because users who do not read Chinese may approve file-system access without fully understanding that the skill wants to scan local resources and write scan-report.json.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill instructs the agent to persist user corrections, including snippets of generated output and requested changes, to a local feedback log without requiring any user-facing disclosure about storage, retention, or possible inclusion of sensitive project content. In this skill’s context, corrections may contain proprietary UI designs, internal component names, or app behavior details copied from Figma-derived output, so silent persistence creates a real privacy and data-handling risk.

External Transmission

Medium
Category
Data Exfiltration
Content
def export_svgs(file_key: str, node_ids: list, token: str) -> dict:
    """Export nodes as SVG via Figma API. Returns {node_id: svg_string}."""
    ids_param = ",".join(node_ids)
    url = f"https://api.figma.com/v1/images/{file_key}?ids={ids_param}&format=svg"
    headers = {"X-Figma-Token": token}
    _rate_limit()
    resp = requests.get(url, headers=headers, timeout=30)
Confidence
88% confidence
Finding
https://api.figma.com/

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.