ClawHub
Back to skill

Security audit

多模型路由器

Security checks for vulnerabilities and agentic risk

Overview

This skill is a non-executable guide for choosing AI models by task type, with no hidden install steps or persistence.

Before installing, note that this skill may activate on common Chinese phrases about model choice or cost optimization, so users who do not want automatic model-routing advice should invoke it explicitly or adjust its trigger wording. No bundled code, install action, credential use, or persistence was found.

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 top-level description is written entirely in Chinese and does not indicate that the skill can operate in other languages or follow the user's preferred locale. Under the policy, language constraints should not be forced without user opt-in or a clearly documented justification.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The activation phrase set includes very generic triggers such as “选择模型 / 路由模型 / 成本优化”, which can plausibly appear in ordinary user requests and cause unintended skill activation. In a routing skill, accidental activation can alter model selection behavior, cost, and response handling without the user explicitly intending to invoke this capability.

Static analysis

No suspicious patterns detected.