ClawHub
Back to skill

Security audit

Security Auditor

Security checks across malware telemetry and agentic risk

Overview

This skill appears to provide security-audit guidance without evidence of hidden execution, persistence, or data exfiltration.

Install this if you want an agent to help review code and security practices. Because the activation terms are broad, users should expect it may engage during general security-related conversations and should still review any proposed file reads, commands, or code changes before allowing them.

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 (1)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger list is unusually broad for auto-activation, including generic terms like 'security', 'audit', 'authentication', and 'validate input' that can match many benign conversations. In an agent ecosystem, this increases the chance the skill is invoked outside narrowly intended contexts, expanding exposure to sensitive code, secrets, or decision-making authority and making prompt-collision or unwanted behavior more likely.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
SKILL.md:91