ClawHub
Back to skill

Security audit

find-skills

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward skill-discovery helper, but users should approve any global skill installation carefully.

Before installing, confirm the exact skill source and trust the publisher. Treat global installs as persistent changes to your agent environment, and ask the agent to show the package and install command before it runs anything.

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 (3)

Vague Triggers

Medium
Confidence
86% confidence
Finding
The description and trigger language are broad enough to match many ordinary help-seeking prompts, which can cause this skill to activate when the user did not explicitly ask to search for or install external skills. In this context, unintended activation matters because the skill can steer the agent toward recommending or installing third-party packages, expanding attack surface and increasing the chance of supply-chain exposure.

Vague Triggers

Medium
Confidence
89% confidence
Finding
The invocation guidance lists many ambiguous conditions like 'how do I do X' and 'can you do X,' without boundaries for when the agent should instead answer directly. That ambiguity can cause over-invocation of a package-discovery workflow, leading the agent to unnecessarily consult or install external skills for routine requests.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill tells the agent it can install with `-g -y`, which performs a global system modification and suppresses confirmation prompts. In a skill whose purpose is discovering third-party packages, this is especially risky because it reduces user friction around installing untrusted code and can lead to accidental or unsafe supply-chain changes on the host environment.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.