ClawHub
Back to skill

Security audit

切换 LLM 端点（OpenAI 兼容第三方）

Security checks for vulnerabilities and agentic risk

Overview

This is a troubleshooting guide for switching OpenAI-compatible LLM endpoints, with no executable code, persistence, or hidden high-impact behavior.

Before installing, understand that this skill is a Chinese-language endpoint-switching checklist. Use it when you are intentionally debugging OpenAI-compatible LLM base URLs, models, status codes, or API key behavior, and avoid logging or committing real API keys while following its examples.

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
88% confidence
Finding

The invocation triggers are broad natural-language troubleshooting phrases such as 'AI 调用失败' and '怎么切模型', which can match many ordinary user requests outside the narrow intended context. This can cause the skill to activate too often and steer the agent into applying endpoint-switching guidance in unrelated situations, increasing the chance of incorrect advice or unnecessary handling of API configuration details.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

All user-facing natural-language metadata in this file is written as Chinese-only guidance, with no indication that the skill supports other languages or that Chinese is required for a region-specific purpose. Under the stated policy, forcing a specific language without user opt-in can be a locale-policy violation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.