ClawHub
Back to skill

Security audit

penetration-tester

Security checks across malware telemetry and agentic risk

Overview

This is a dual-use penetration-testing instruction skill, but its risky topics are disclosed, purpose-aligned, and framed around authorization and scope.

Install only for authorized security assessments. Before using it with real tools, define the approved targets, scope, rules of engagement, escalation contacts, and human approval points for intrusive steps such as scanning, exploitation, social engineering, persistence testing, or exfiltration simulation.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill explicitly instructs the agent to perform high-risk penetration-testing activities such as port scanning, exploit validation, persistence analysis, social engineering, and post-exploitation, but it does not require a strong user-facing warning or hard safety gate before those actions are proposed or executed. In an agent setting, this increases the chance of unauthorized, disruptive, or legally sensitive guidance being provided under ambiguous prompts, even though the stated framing is ethical testing.

VirusTotal

58/58 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.