Security audit

Cn Web Search Custom

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese web-search helper that sends search terms to listed search engines, with no local code, persistence, or credential access found.

Install this if you want a Chinese-oriented search helper that queries multiple public search engines. Avoid using it for secrets, private customer data, credentials, or sensitive personal information because search terms are sent to external sites.

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 (4)

Vague Triggers

Medium

Confidence: 91% confidence
Finding: The example trigger phrase is broad natural-language wording that can easily overlap with ordinary user conversation, increasing the chance the skill is invoked unintentionally. In an agent environment, accidental invocation can cause unexpected web-scraping behavior, unnecessary external requests, and unintended exposure of user queries to third-party search sites.

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The skill explicitly instructs the agent to send raw user queries to multiple third-party search engines via web scraping, but it provides no privacy warning, consent step, or guidance to avoid transmitting sensitive information. In an agent context, users may submit confidential business, personal, or regulated data as search terms, which would then be disclosed to external services and logged by those providers.

Natural-Language Policy Violations

Low

Confidence: 80% confidence
Finding: The skill description and usage are entirely framed around Chinese-language interaction (for example, Chinese title and Chinese-only invocation examples) without stating that language choice is optional. This can be a natural-language locale policy issue if users are not given an explicit opt-in or alternative language path.

Natural-Language Policy Violations

Low

Confidence: 88% confidence
Finding: The package description explicitly presents the skill as a Chinese-language web search tool ("中文网页搜索") without indicating any user choice of language or locale. Under the stated policy, forcing a specific language without opt-in can be a natural-language policy violation unless the locale constraint is clearly documented and justified.

Static analysis

No suspicious patterns detected.