ClawHub
Back to skill

Security audit

Openclaw Free Models

Security checks for vulnerabilities and agentic risk

Overview

This is a visible Markdown guide for configuring OpenClaw model providers, with no hidden code or automatic actions, but users should understand that API keys and prompts may go to the selected provider.

Before installing or following the guide, confirm the current pricing and free-quota terms with each provider, use only API keys you are comfortable storing in OpenClaw configuration, and avoid sending sensitive prompts unless you trust the selected provider's data handling. Running the sample config commands will change future OpenClaw model/API-key behavior until you change it again.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

External Model or Provider Selection

High
Category
Excessive Agency
Content
openclaw config get model

# 临时切换
openclaw ask "问题" --model deepseek-chat
```

## 成本对比
Confidence
90% confidence
Finding
Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill instructs users to set API keys for third-party providers but does not warn that the credentials will be stored locally in OpenClaw configuration and used to transmit prompts and metadata to external services. This can mislead users into exposing paid credentials or sensitive prompts without understanding the storage and data-sharing implications.

External Transmission

Medium
Category
Data Exfiltration
Content
```bash
# DeepSeek
curl https://api.deepseek.com/user/balance -H "Authorization: Bearer $API_KEY"

# GLM
curl https://open.bigmodel.cn/api/paas/v4/balance -H "Authorization: Bearer $API_KEY"
Confidence
50% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Natural-Language Policy Violations

Low
Confidence
95% confidence
Finding
The description and instructions force a single language for all users, and there is no opt-in, alternative language, or statement that the skill is only for a Chinese-speaking audience. The rule specifically flags language or locale policy violations when a skill mandates a language without user choice or documented justification.

Static analysis

No suspicious patterns detected.