Security audit

Proxy Auto

Security checks for vulnerabilities and agentic risk

Overview

The skill is a proxy helper with no obvious malicious code, but it can route sensitive service traffic through an under-specified proxy without enough user control or disclosure.

Install only if you intentionally want agent network requests routed through this proxy setup. Before using it with API calls, package installs, or private repositories, verify who controls the VMess/Singapore backend, what data may pass through it, and how to disable the proxy. Avoid using it for secrets or regulated data unless that proxy path is trusted and approved.

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
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (5)

Missing User Warnings

Medium

Confidence: 91% confidence
Finding: The skill explicitly instructs users to route traffic through a local SOCKS5/HTTP proxy to reach third-party services such as GitHub and OpenAI, but it provides no warning that requests, prompts, credentials, package downloads, and other metadata may be transmitted through external infrastructure. In a security-sensitive agent environment, undocumented proxying can change trust boundaries, create privacy/compliance issues, and expose sensitive data if users assume direct connections.

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: The file contains user-facing natural language in Chinese, including the runtime disclosure message on L19, with no indication that the user can choose another language or that the script is intentionally limited to a Chinese-speaking context. This can violate language/locale policy when a skill forces a specific language without user opt-in.

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The description says the skill will automatically enable a VMess proxy 'when external network access is needed' without defining clear triggers, approval flow, or scope. Ambiguous automatic activation of a network proxy can route traffic unexpectedly, weaken user visibility into network behavior, and create opportunities for misuse or policy bypass if the agent decides on its own when to enable the proxy.

Natural-Language Policy Violations

Medium

Confidence: 71% confidence
Finding: The natural-language description is presented only in Chinese and does not indicate that users can choose another language or that the skill is intentionally limited to a Chinese-speaking context. This may violate language or locale policy when no opt-in or justification is provided.

Natural-Language Policy Violations

Low

Confidence: 83% confidence
Finding: SQP-3 applies to all file types and covers language or locale policy violations. The skill content is presented entirely in Chinese, and there is no indication that this locale is optional, user-selected, or required for a documented region-specific purpose.

Static analysis

No suspicious patterns detected.