Back to skill

Security audit

百度搜索

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Baidu web search helper that sends user search queries to Baidu using a required API key, with no evidence of persistence, hidden behavior, or destructive actions.

Before installing, understand that any query you submit will be sent to Baidu's search API using your BAIDU_API_KEY. Avoid searching for secrets, regulated personal data, or confidential internal material unless sharing it with that provider is approved.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (6)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding

The skill invokes code that uses environment variables and makes outbound network requests, but the manifest does not declare an explicit tool scope such as permissions or allowed-tools. This weakens policy enforcement and user visibility, making it easier for the skill to access sensitive capabilities without clear declaration or review.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill description says it performs web search but does not clearly disclose that user queries are transmitted to Baidu's external API using an API key. This can lead users to provide sensitive prompts or internal data without understanding that the content leaves the local system and is shared with a third party.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
80% 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.py (reported line 19)May include surrounding context.

python
}

    # 使用POST方法发送JSON数据
    response = requests.post(url, json=requestBody, headers=headers)
    response.raise_for_status()
    results = response.json()
    if "code" in results:

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill sends the user-provided query to Baidu's external search service, which can expose sensitive user input to a third party if users are unaware of the data flow. In a search skill this transmission is expected, but the lack of explicit disclosure or consent can still create a privacy and data-handling risk, especially if users submit secrets, internal data, or regulated content.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The only concrete example queries are in Chinese and the skill is branded around Baidu, which suggests a Chinese-language default experience, but the documentation does not state whether other languages are supported or whether Chinese is required. Under the policy, forcing or implying a specific language without opt-in can be a natural-language policy issue unless the locale constraint is explicitly documented and justified.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The stated purpose is to search the web using Baidu's search service. While outbound HTTP is expected for that purpose, reading process environment state to obtain secrets is an additional capability not reflected in the manifest description. This is a mild intent mismatch because the code depends on credential access beyond the user-visible search behavior.

Content

No source excerpt is available for this finding.