ClawHub
Back to skill

Security audit

Security Audit Toolkit

Security checks across malware telemetry and agentic risk

Overview

This is a coherent security-audit checklist, but users should handle any secret-scan output and automatic fixes carefully.

Install this for workspaces you are comfortable auditing. Treat detected secrets as sensitive, rotate any real credentials found, review dependency auto-fix diffs before committing, and only add the pre-commit hook if you want local commit blocking; avoid using --no-verify unless you have a reviewed exception.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • 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)

Tool Parameter Abuse

High
Category
Tool Misuse
Content
if [ $EXIT_CODE -ne 0 ]; then
    echo ""
    echo "To proceed anyway: git commit --no-verify"
    echo "To remove secrets: replace with environment variables"
fi
exit $EXIT_CODE
Confidence
84% confidence
Finding
--no-verify

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.