ClawHub
Back to skill

Security audit

Baidu Search

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward Baidu web-search helper, with a privacy caution because it echoes the submitted query before returning results.

Install only if you are comfortable sending search queries to Baidu's Qianfan API and having the submitted query echoed in command output. Avoid putting secrets or highly sensitive text in the query field; make sure BAIDU_API_KEY and the Python requests package are available in the runtime.

SkillSpector

By NVIDIA
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 (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding
The skill metadata declares required environment variables and the documented script performs live web search, which implies access to both secrets and outbound network capabilities, yet no explicit permissions are declared. This creates a trust and policy-enforcement gap: a caller or platform may underestimate the skill's access, allowing a search tool to read sensitive configuration and make external requests without clear consent boundaries.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The script prints the fully parsed request body to stdout, which includes the user's search query and potentially other user-supplied fields. In agent or hosted environments, stdout is commonly captured in logs, creating an unintended disclosure path for sensitive user input such as internal research topics, credentials pasted by mistake, or other private data.

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.