Back to skill

Security audit

Tianshu Baidu Search

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Baidu web search helper that sends the user's search query to Baidu using a disclosed API key.

Install this only if you are comfortable sending search queries to Baidu's Qianfan AI Search API and providing a BAIDU_API_KEY in the environment. Avoid using it for sensitive queries unless that is acceptable under your Baidu account and data-handling expectations.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding

The skill declares access to an environment variable and uses network-capable code, but it does not explicitly constrain tool scope with permissions or allowed-tools. This creates an authorization gap where the runtime may grant broader capabilities than reviewers or users expect, increasing the risk of secret exposure or unintended outbound requests if the implementation changes or is abused.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file’s user-facing description and usage examples are entirely in Chinese, including the stated purpose and required JSON fields, with no indication that other languages are supported. This creates a language/locale constraint in natural-language guidance without user opt-in or justification.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
70% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/search.js (reported line 67)May include surrounding context.

js
};

async function main() {
  const res = await fetch('https://qianfan.baidubce.com/v2/ai_search/web_search', {
    method: 'POST',
    headers: {
      Authorization: `Bearer ${apiKey}`,

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
77% confidence
Finding

The natural-language metadata prominently presents the skill as "百度 AI 搜索" / Baidu search and does not indicate any user language or locale choice. This can be read as a locale-specific constraint without an explicit opt-in or justification in the manifest text.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.