ClawHub
Back to skill

Security audit

red-team-pro

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Chinese red-team review skill that may be blunt or over-eager, but it does not show hidden access, execution, data theft, or destructive behavior.

Install this only if you want direct, adversarial critique of plans or decisions. Expect it to challenge ideas aggressively and to default to Chinese; also verify the package name because the marketplace metadata and README install command do not use the same name.

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 (3)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The trigger conditions are broad enough to match many normal discussions about plans, risks, or decision-making, which can cause the skill to activate when the user did not explicitly ask for an adversarial review. In a skill designed to be intentionally oppositional, unintended invocation can derail user intent, produce needlessly aggressive output, and suppress more appropriate workflows.

Natural-Language Policy Violations

Medium
Confidence
77% confidence
Finding
The skill metadata hard-codes a Chinese locale without indicating that language should follow the user's preference. This can create usability and transparency issues, especially in multilingual environments, and may cause the skill to respond in an unexpected language or be selected inappropriately for users who did not request Chinese output.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger example '帮我找找这个方案的漏洞' is broad enough to match many normal advisory or brainstorming requests, so the skill may activate outside clearly intended red-team contexts. In this skill, over-triggering is meaningful because it steers the assistant into an adversarial posture by default, which can distort otherwise balanced guidance and cause unnecessary negative framing.

VirusTotal

59/59 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.