ClawHub
Back to skill

Security audit

Code Metrics

Security checks across malware telemetry and agentic risk

Overview

This skill is a local, read-only code metrics tool with no evidence of hidden network access, credential handling, persistence, or destructive behavior.

Install only if you want repository-wide code metrics. Run it on projects you intend to inspect, and review reports before sharing because they can include file paths, function names, and project structure. The broad trigger wording may cause the skill to activate for general code overview requests.

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
78% confidence
Finding
The description contains broad activation phrases such as 'analyze code quality,' 'get a project overview,' and 'audit code metrics across a codebase,' which can overlap with many common development requests and cause the skill to be invoked more often than intended. In a skill that reads repository contents, over-broad triggering increases unnecessary exposure of local code and metadata, even if the skill itself appears read-only.

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.