ClawHub
Back to skill

Security audit

Find Skills Pro

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent skill finder, but it should be reviewed because it can steer agents toward broad third-party skill discovery and global installs that skip confirmation.

Use this skill only when you actually want help finding installable skills. Before installing anything it suggests, review the publisher and source link, prefer an install command without `-y`, and avoid global installs unless you intentionally want the skill to affect future agent sessions.

SkillSpector

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
84% confidence
Finding
The metadata description defines activation using very broad natural-language examples such as 'how do I do X' and 'can you do X', which are common across many ordinary requests. This can cause the skill to trigger in situations where the user is not actually asking to discover or install external skills, leading the agent toward package discovery or installation flows unnecessarily.

Vague Triggers

Medium
Confidence
87% confidence
Finding
The listed 'When to Use This Skill' conditions are ambiguous and overlap with generic assistant behavior, especially prompts like asking 'how do I do X' or expressing interest in help for a domain. In context, this is risky because the skill is explicitly connected to discovering and installing third-party skills, so overbroad activation can steer users into supply-chain-affecting actions without clear intent.

Missing User Warnings

High
Confidence
97% confidence
Finding
The skill recommends `npx skills add <owner/repo@skill> -g -y`, which performs a global installation and suppresses confirmation prompts, but it does not require explicit user consent or present any warning about modifying the local environment. In a skill-discovery context, this is especially dangerous because it normalizes installing third-party packages from external sources, increasing the chance of unintended system changes or supply-chain compromise.

Static analysis

No suspicious patterns detected.