ClawHub
Back to skill

Security audit

管理体系整合技能

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only helper for integrating ISO-style management systems, with no executable code, network behavior, persistence, or hidden data handling.

Before installing, users should understand that the skill may process internal management-system details they provide in chat and generate template documents; review generated compliance materials before business use. No evidence was found of code execution, remote calls, credential use, persistence, or data exfiltration.

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
89% confidence
Finding

The trigger conditions are broad enough that the skill could be invoked for loosely related requests about management systems, optimization, or integration. In an agent environment, over-broad activation can cause inappropriate routing, unexpected document generation, or disclosure/processing of user-supplied business information in the wrong workflow, even though the skill itself is non-executable and domain-specific.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

L200 明确写出“支持中文交互”，在自然语言层面体现出对特定语言的预设，但文档中未说明是否也支持其他语言，亦未提供用户选择语言的机制。根据语言/locale 政策，若技能对语言有约束，应有明确的用户选择或合理限定说明。

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.