ClawHub
Back to skill

Security audit

penetration-tester

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed penetration-testing guidance skill with no bundled code, persistence, or hidden install behavior, but it should only be used on clearly authorized targets.

Install only if you need penetration-testing assistance, and use it only for systems where you have explicit authorization, defined scope, rules of engagement, and a plan to avoid disruption or exposure of sensitive data.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

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
Category
Not specified by scanner
Confidence
93% confidence
Finding

The invocation section describes broad penetration-testing behavior but does not constrain when the skill may be activated or require a strong authorization gate before proceeding. In a high-risk offensive-security skill, ambiguous triggers increase the chance of misuse, overbroad execution, or the agent performing dual-use security actions without sufficiently verified scope and approval.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.