ClawHub
Back to skill

Security audit

QwenPaw MCP Helper

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward QwenPaw MCP diagnostic helper, with expected local config reads and connection checks but no evidence of hidden installation, persistence, exfiltration, or remote code execution.

Install this only if you want a Chinese-language helper for QwenPaw MCP troubleshooting. Running it may display local MCP configuration details and send connection probes to every MCP server configured in QwenPaw, so review configured endpoints first if your environment includes private or sensitive internal services.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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
Findings (3)

External Script Fetching

High
Category
Supply Chain
Confidence
90% confidence
Finding

Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.

Content

Scanner excerpt · SKILL.md (reported line 11)May include surrounding context.

md
bins:
        - qwenpaw
        - python3
        - curl
      env: []
---

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill instructs active outbound probing of every configured MCP server via curl, but it does not clearly warn the user that running the diagnostic will generate network traffic and reveal configured endpoints to the local execution environment. In a security-sensitive environment, this can unintentionally touch internal services, trigger monitoring, or expose private infrastructure details through logs and command history.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The natural-language instructions and examples are presented only in Chinese, which can impose a fixed language on users without opt-in. The policy requires either offering a language/locale choice or clearly documenting and justifying a locale-specific constraint.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.