ClawHub
Back to skill

Security audit

Proxy Cn

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed local proxy helper that only sets proxy environment variables for user-directed commands.

Install this only if you intentionally want selected commands or a shell session to use your local proxy. Prefer the one-command wrapper for temporary use, and remember that commands run through the proxy may expose destination and traffic metadata to your local proxy software or upstream proxy provider. The documented PowerShell entry points are missing from this artifact, so Windows PowerShell usage may not work as described.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding
The skill explicitly instructs use of shell/PowerShell scripts and command execution, but it does not declare any tool scope such as permissions or allowed-tools. That creates a governance gap: an agent may execute shell-capable behavior without an explicit least-privilege boundary, increasing the chance of unintended command execution or misuse in environments that rely on metadata for enforcement.

Rp1

Medium
Category
MCP Rug Pull
Confidence
75% confidence
Finding
Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.

Natural-Language Policy Violations

Low
Confidence
96% confidence
Finding
The comments and usage instructions are written entirely in Chinese, and the emitted status message is also Chinese. For a general-purpose shell skill, this imposes a specific language on users without offering a language/locale choice or documenting a justified region-specific limitation.

Natural-Language Policy Violations

Low
Confidence
97% confidence
Finding
The comments and runtime messages in this shell script are entirely in Chinese, including usage/help output and status disclosures. Because the file does not indicate that the skill is intentionally region-specific or provide any user opt-in for language selection, it violates the language/locale policy criteria.

Static analysis

No suspicious patterns detected.