ClawHub
Back to skill

Security audit

告别不规范代码，让 AI 成为你的代码质量守护者

Security checks across malware telemetry and agentic risk

Overview

This skill appears to be a code-style assistant that locally inspects project files to apply coding standards, with no evidence of hidden networking, credential access, or destructive behavior.

Install this if you want coding standards applied during code generation and review. Run the analyzer only against the intended project directory, review any project .coderules.json before relying on it, and remember that broad triggers may make the skill influence routine coding tasks.

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
90% confidence
Finding
The trigger phrases are very broad, including generic terms like '生成代码' and '代码审查', which can cause the skill to activate for many ordinary coding requests beyond its intended niche. Over-broad activation increases the chance that unrelated tasks are steered by this skill’s rigid instructions, potentially causing unintended file inspection, unwanted workflow changes, or policy interference in contexts where the user did not request code-rules enforcement.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.