ClawHub
Back to skill

Security audit

逆向工程Agent

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Chinese-language technical analysis guide for publicly observable product research and does not install code, persist, or request privileged access.

Install this only if you want a Chinese-language framework for lawful, public-source technical due diligence or competitor/product analysis. Do not use it for unauthorized probing, bypassing access controls, credential abuse, or extracting private system prompts or proprietary internals from systems you are not allowed to assess.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill description is very broad, claiming capability to analyze nearly any product, platform, or system without defining boundaries, allowed targets, or user-trigger constraints. In a reverse-engineering context, that ambiguity increases the chance the skill will be invoked for sensitive dual-use tasks such as competitor surveillance, unauthorized technical probing, or analysis of proprietary systems beyond intended scope.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
76% confidence
Finding

The display name and description are written entirely in Chinese, with no indication that users may choose another language or locale. This can constitute a language-policy issue when a skill implicitly enforces a specific language without documenting user choice or a justified region-specific constraint.

Content

No source excerpt is available for this finding.