ClawHub
Back to skill

Security audit

QwenPaw Upgrade Assistant

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed QwenPaw upgrade-check helper that reads version and release information without performing upgrades or persistent changes.

Install only if you are comfortable with a helper that runs qwenpaw --version, contacts PyPI and the QwenPaw release-notes site, and may inspect QwenPaw-related skills, plugins, or MCP settings to assess compatibility. It should not perform the upgrade automatically or request credentials.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

External Script Fetching

Low
Category
Supply Chain
Confidence
15% 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: []
---

External Script Fetching

Low
Category
Supply Chain
Confidence
15% 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: []
---

Static analysis

No suspicious patterns detected.