ClawHub
Back to skill

Security audit

Unix

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed Chinese engineering workflow guide with no executable code, persistence, credential handling, or hidden data access.

Install this if you want a strict Chinese-language engineering workflow that asks clarifying questions before coding. Be aware that its trigger wording is broad, so you may want to invoke it explicitly with /unix if you do not want it shaping ordinary requests.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The skill advertises activation on broad natural-language cues such as any user input containing a requirement, 'Unix', '/unix', or requests for rigorous analysis/minimal-cost delivery. This can cause unintended invocation in unrelated conversations, unexpectedly overriding the assistant’s normal behavior and steering responses into a rigid workflow the user did not explicitly request.

Natural-Language Policy Violations

Medium
Confidence
92% confidence
Finding
The metadata and instructions are written to enforce Chinese-language behavior without checking the user’s language preference. If auto-invoked, this can degrade usability, confuse users, and create prompt-routing mismatches where the assistant responds in an unexpected language despite the surrounding conversation being in another language.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.