ClawHub
Back to skill

Security audit

Crxjs

Security checks across malware telemetry and agentic risk

Overview

The skill is normal CRXJS development guidance, but it grants broad GitHub CLI authority that is not explained by the skill’s purpose.

Install only if you are comfortable supervising its tool access. The CRXJS guidance itself is ordinary, but consider restricting or ignoring GitHub CLI access unless a specific task requires it, review npm-generated project files before running them, and narrow copied Chrome extension permissions and URL match patterns before publishing.

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
82% confidence
Finding
The trigger description is broad enough to match generic Chrome extension queries that should be handled by a more general architecture skill. In an agent system, over-broad invocation can route users into a specialized skill with narrower assumptions, causing incorrect guidance, missed security considerations, or tool use in the wrong context.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.