Back to skill

Security audit

Baidu Search 1 1 0.Skip

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Baidu web search helper that sends user-provided search queries to Baidu's API using a required API key.

Install only if you intend to send search queries to Baidu's AI Search service and are comfortable providing BAIDU_API_KEY. Non-Chinese readers may need to translate parts of the usage documentation before invoking it.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding

The skill documentation indicates capabilities involving environment variables, file input, and network access, but it does not declare an explicit tool scope such as permissions or allowed-tools. This creates an authorization and review gap: consumers cannot easily tell what the skill is permitted to access, and an agent framework may grant broader access than intended.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

This markdown file contains core usage instructions, parameter descriptions, and troubleshooting primarily in Chinese, which effectively forces a specific language for users who may not understand it. The policy allows locale constraints only when clearly justified or when the user is offered a language choice, neither of which is present here.

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 16)May include surrounding context.

python
"Content-Type": "application/json"
    }

    response = requests.post(url, json=requestBody, headers=headers, timeout=25)
    response.raise_for_status()
    results = response.json()
    if "code" in results: