ClawHub
Back to skill

Security audit

Language Specialist

Security checks across malware telemetry and agentic risk

Overview

This is a broad coding guidance skill with no executable components or hidden data access, though it may apply to many programming requests.

Install this if you want broad programming-language guidance to shape coding responses. Be aware it may influence many development tasks, so users who prefer narrower, opt-in behavior may want a more language-specific skill.

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
92% confidence
Finding
The trigger conditions are extremely broad and match a large share of normal software-engineering requests, so this skill may auto-activate in situations where the user did not specifically request it. Over-broad activation increases the chance that hidden behavioral instructions inside the skill override or bias the assistant's normal handling, creating prompt-scope and least-surprise issues rather than a direct code-execution exploit.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.