ClawHub
Back to skill

Security audit

Argument Audit

Security checks across malware telemetry and agentic risk

Overview

This skill is a straightforward argument-analysis tool, with a privacy caveat for examples involving workplace chat logs.

Installers should avoid pasting full chat exports or confidential workplace records into the skill. Use short, relevant excerpts, redact names and sensitive details, and make sure they have permission to analyze any third-party messages.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The WeChat chat-analysis scenario explicitly encourages processing workplace conversation records without any privacy warning, consent guidance, or data-minimization instruction. Because chat logs can contain sensitive personal, employment, or confidential business information, this omission can lead users to paste or export third-party data into the system without authorization.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The description defines broad natural-language activation criteria such as multiple generic analysis intents ('论点分析、论证评估、逻辑审查、观点评估' and 'analyze the strength and validity of an argument') without clear exclusions or routing boundaries. This can cause over-triggering or unintended invocation on loosely related user requests, which may lead to incorrect tool selection, user confusion, or bypass of more appropriate skills.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.