ClawHub
Back to skill

Security audit

Skill Vetter

Security checks across malware telemetry and agentic risk

Overview

This skill is a lightweight skill-vetting helper with some overconfident wording, but its behavior is disclosed, purpose-aligned, and not destructive or hidden.

Use this as a quick pre-screen only. Do not rely on its 'Install' or 'safe to install' wording as proof that a skill is safe; manually review high-impact permissions, network destinations, credential handling, hooks, and install scripts before installing third-party skills.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Intent-Code Divergence

Medium
Confidence
97% confidence
Finding
The script presents itself as a security vetting tool and ultimately outputs strong assurances such as 'safe to install' based on very limited checks: metadata parsing, a few grep-based signatures, and documentation length/keywords. This can create false trust and cause users to install malicious or unsafe skills that evade these shallow heuristics.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The trigger list is broad enough to match generic requests like 'check this skill' or 'review skill', which can cause this skill to activate outside narrowly intended contexts. Because the skill instructs the agent to trust ClawHub's automated security status ('trust them'), an unintended invocation could bias security decisions and reduce scrutiny of untrusted content.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.exposed_secret_literal, suspicious.generated_source_template_injection

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
references/credential-patterns.md:7

User-controlled placeholder is embedded directly into generated source code.

Critical
Code
suspicious.generated_source_template_injection
Location
references/credential-patterns.md:19