ClawHub
Back to skill

Security audit

Figma设计工具v2

Security checks for vulnerabilities and agentic risk

Overview

This Figma skill appears to be a mostly generic automation template that asks for broad read, write, and command-execution authority beyond its stated Figma integration purpose.

Review before installing. Use this only in an agent environment where read, write, and command execution can be constrained, and prefer granting it only for explicit Figma tasks with a known Figma credential. Do not rely on the artifact's generic sandbox or whitelist language unless your host actually enforces those controls.

SkillSpector

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Context-Inappropriate Capability

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill advertises system command execution even though its stated purpose is Figma API integration, creating unnecessary exposure to arbitrary local command execution. In an agent environment with broad activation language and generic workflow descriptions, this can cause the skill to be selected for tasks unrelated to Figma and expand a simple API connector into a host-level execution surface.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The activation text is overly broad, inviting use for generic efficiency, automation, batch processing, and workflow optimization rather than clearly limiting use to Figma tasks. In agentic systems, vague matching language can cause inappropriate tool selection, which becomes more dangerous here because the skill also declares read, write, and exec capabilities.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The scenario examples describe generic file, image, and token operations without constraining them to Figma workflows, which can bias an agent toward invoking the skill for unrelated tasks. Given the declared write and exec capabilities, this scope ambiguity increases the risk of misuse beyond the intended API-integration context.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.