ClawHub
Back to skill

Security audit

llama-params-optimizer

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed local llama.cpp tuning guide; its commands and configuration examples fit that purpose.

Installers should treat the commands as examples, keep llama-server bound to localhost unless they add proper reverse proxy and HTTPS controls, avoid using sensitive prompts when testing cloud models, and verify any systemd or OpenClaw config changes against their own hardware.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (5)

External Transmission

Medium
Category
Data Exfiltration
Content
**📋 验证方法：**
```bash
# 标准 curl 测速命令（固定 temperature=0.7, max_tokens=100）
curl -s http://localhost:8080/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"messages":[{"role":"user","content":"请写一段500字左右的技术博客文章，讨论本地部署大语言模型的性能优化方法"}],"max_tokens":100,"temperature":0.7}'
Confidence
60% 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
86% confidence
Finding
This markdown file contains user-facing natural language that largely defaults to Chinese, while only one entry mentions bilingual support in a past version note. That can conflict with a language/locale policy requiring user choice, because the current file itself does not provide an explicit opt-in or alternative language presentation.

Natural-Language Policy Violations

Low
Confidence
77% confidence
Finding
The document is bilingual overall, but the concrete curl validation example hardcodes a Chinese user prompt and many operational examples are primarily written in Chinese. This can be a locale-policy concern because the skill does not clearly state that users may substitute prompts in their preferred language or that Chinese is merely illustrative.

Natural-Language Policy Violations

Low
Confidence
92% confidence
Finding
The description field uses only Chinese text, which can impose a language constraint on users without any opt-in or explanation. The policy explicitly calls for flagging language or locale restrictions unless the skill offers a choice or clearly documents a justified locale-specific scope.

Natural-Language Policy Violations

Low
Confidence
95% confidence
Finding
This markdown file contains user-facing natural language exclusively in Chinese, and there is no indication that the user can choose another language or that the content is intentionally limited to a Chinese-speaking audience. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Static analysis

No suspicious patterns detected.