ClawHub
Back to skill

Security audit

Logo设计指南(免费版)

Security checks across malware telemetry and agentic risk

Overview

This skill is a logo design and export guide with local file-generation examples, and I found no hidden or purpose-mismatched behavior.

Before installing, treat this as a Chinese-language logo workflow guide. Review any sample ImageMagick, rsvg-convert, or Python commands before running them, especially because they create or overwrite local icon and manifest outputs.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The description is extremely broad and repeatedly claims applicability to generic development scenarios, which can cause the skill to activate outside its intended logo-design context. In an agent environment with read/exec/write permissions, weak trigger boundaries increase the chance of unintended invocation and unnecessary exposure of privileged tooling.

Natural-Language Policy Violations

Medium
Confidence
79% confidence
Finding
The skill name/display metadata strongly enforce Chinese presentation without any indication that language should follow user preference. This can override user expectations, reduce transparency, and increase the risk that instructions or generated commands are misunderstood in multilingual workflows.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.