ClawHub
Back to skill

Security audit

Clawaudit

Security checks across malware telemetry and agentic risk

Overview

This skill is only an informational placeholder and does not currently run code, install anything, or request access to repositories or credentials.

Safe to install as a placeholder. Treat future versions differently if they add scanning code, repository access, credentials, or upload behavior, and only submit repositories you own or have explicit permission to analyze.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill encourages users to manually add any repository they care about but provides no warning about privacy, consent, or data-handling implications. In a security-checking context, this can mislead users into submitting private, third-party, or sensitive repositories without understanding exposure, authorization, or retention risks.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.