ClawHub
Back to skill

Security audit

Find Skills (Robin's Fork)

Security checks across malware telemetry and agentic risk

Overview

This skill does what it says, but it can steer broad help requests into installing third-party skills globally with confirmation prompts skipped.

Install only if you want the agent to search external skill sources and potentially add persistent new skills. Before any install, review the package source and publisher, avoid auto-confirm installs unless you are sure, and prefer scoped or reversible installs where available.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
87% confidence
Finding
The skill description says it should be used whenever users ask broad questions like 'how do I do X' or express interest in extending capabilities, which overlaps with many normal requests. That can cause the skill to activate too often and steer ordinary conversations into package discovery or installation flows, increasing the chance of unnecessary third-party skill suggestions.

Vague Triggers

Medium
Confidence
89% confidence
Finding
The activation guidance includes ambiguous criteria such as users asking 'can you do X' or mentioning they wish they had help with a domain, without requiring a clear request to search for installable skills. In context, this makes accidental invocation more likely and can push users toward external package installation when a direct answer would be safer and sufficient.

Missing User Warnings

High
Confidence
97% confidence
Finding
The skill recommends installing third-party packages with `npx skills add <owner/repo@skill> -g -y`, which performs a global installation and suppresses confirmation prompts. This is dangerous because it encourages system-impacting changes from potentially untrusted external sources without review, increasing the risk of supply-chain compromise or unintended persistent modifications to the user's environment.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.