ClawHub

Agentic Security Audit

Security checks across malware telemetry and agentic risk

Overview

This is a visible security-audit skill with purpose-aligned commands, but users should review commands before running them and avoid bypassing its secret-check hook.

Install this only if you want an audit checklist and command snippets for security review. Run commands in a trusted workspace, avoid sharing raw scan output because it may contain secrets, use dependency-fix commands on a branch, and do not use the hook bypass except through a deliberate exception process.

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
91% confidence
Finding
--no-verify

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal