ClawHub
Back to skill

Security audit

逆向工程Agent

Security checks across malware telemetry and agentic risk

Overview

This is a text-only reverse-engineering analysis skill that is broad and dual-use, but its artifacts disclose the purpose and limit use to public, lawful observation.

Install only if you want an assistant to help analyze products, competitors, APIs, and agent systems from observable evidence. Use it only on systems you are authorized to assess, and treat its architecture, authentication, database, or prompt conclusions as inferences unless supported by clear evidence.

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
91% confidence
Finding
The manifest description is extremely broad and promises reverse-engineering across many product and platform categories without any stated boundaries, allowed inputs, or safety constraints. In an agent ecosystem, this can cause the skill to be invoked for sensitive analysis tasks beyond the author's likely intent, increasing the chance of misuse for unauthorized reconnaissance or circumvention-oriented assistance.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.