detect opened proxy

• Outcome: Pass
• Latest audit: Sep 11, 2026 · 6:12 AM UTC
• Version: 1.0.0

Overview

This skill locally checks proxy settings and common local proxy ports, which matches its stated purpose and does not show hidden persistence, exfiltration, or destructive behavior.

Before installing, understand that running this skill may reveal whether you use a local proxy and may print the proxy address. It does not appear to send that data elsewhere or modify your system, but use caution in sensitive environments where proxy configuration itself is confidential.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Behavioral AST: exec() Call, eval() Call, Dynamic Import
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

subprocess module call

Medium

• Category: Dangerous Code Execution

Content

try:
        # Query registry for proxy server setting
        cmd = ["reg", "query", "HKEY_CURRENT_USER\\Software\\Microsoft\\Windows\\CurrentVersion\\Internet Settings", "/v", "ProxyServer"]
        output = subprocess.check_output(cmd, universal_newlines=True, stderr=subprocess.STDOUT)
        
        # Parse output to find proxy address
        lines = output.strip().split("\n")

• Confidence: 70% confidence
• Finding: subprocess module calls execute external commands. Without careful input validation, this enables command injection.

subprocess module call

Medium

• Category: Dangerous Code Execution

Content

try:
        # Query registry for proxy server setting
        cmd = ["reg", "query", "HKEY_CURRENT_USER\\Software\\Microsoft\\Windows\\CurrentVersion\\Internet Settings", "/v", "ProxyServer"]
        output = subprocess.check_output(cmd, universal_newlines=True, stderr=subprocess.STDOUT)
        
        # Parse output to find proxy address
        lines = output.strip().split("\n")

• Confidence: 70% confidence
• Finding: subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Missing User Warnings

Low

• Confidence: 94% confidence
• Finding: The skill documentation says it detects system proxy settings, but it does not clearly warn users that it will actively probe local proxy endpoints to determine whether they are running. Even though this is low severity, undocumented inspection of local network configuration and connectivity can surprise users, leak environment details into downstream workflows, or violate least-surprise expectations in security-sensitive environments.

Missing User Warnings

Low

• Confidence: 86% confidence
• Finding: The script performs OS-level inspection of proxy configuration and local proxy ports without any clear user-facing warning or consent mechanism. In an agent skill context, this can disclose environment/network configuration and fingerprint security tooling present on the host, which is sensitive reconnaissance data even if no exploitation occurs.

Static analysis

No suspicious patterns detected.