ClawHub
Back to skill

Security audit

ISO22000标准技能

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language ISO 22000 food safety consulting skill with no executable code, external calls, persistence, or hidden authority.

Before relying on the content for certification work, verify current local food safety laws, certification-body requirements, and product-specific safety limits with qualified compliance professionals. The skill itself does not appear to request risky access or perform actions on your system.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Tp2

High
Category
MCP Tool Poisoning
Confidence
85% confidence
Finding

Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The TRACE section explicitly states the skill 'supports Chinese interaction' (支持中文交互), but the document does not indicate that other languages are supported or that Chinese is optional. This can be read as a language/locale constraint without user opt-in, which falls under the policy check for forced language behavior.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.