ClawHub
Back to skill

Security audit

代码片段管理器

Security checks for vulnerabilities and agentic risk

Overview

This is a simple markdown-only code snippet skill with disclosed local snippet storage and no hidden execution, network, credential, or destructive behavior.

Install this if you want a Chinese-language code snippet helper. Be aware it is designed to keep saved snippets and tags locally, so avoid saving secrets or private credentials in snippets, and consider narrowing trigger phrases if accidental activation would be disruptive.

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)

Natural-Language Policy Violations

Medium
Confidence
88% confidence
Finding
The manifest description, tags, headings, feature list, trigger keywords, and examples are all presented in Chinese, with no indication that other languages are supported or that Chinese is an intentional region-specific constraint. This can violate language/locale policy when a skill implicitly requires a specific language without user opt-in.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The trigger phrases are very broad generic coding terms such as saving, searching, or finding code, which can easily overlap with normal user requests unrelated to this skill. That ambiguity can cause unintended skill activation, leading to incorrect handling of user requests or accidental access/modification of the snippet store when the user only intended a general coding conversation.

Static analysis

No suspicious patterns detected.