ClawHub
Back to skill

Security audit

Baidu web search

Security checks across malware telemetry and agentic risk

Overview

This is a straightforward Baidu web-search skill, but users should treat the Baidu API key and sent search queries as sensitive.

Install only if you are comfortable sending search queries to Baidu or the configured sandbox proxy. Use a dedicated, revocable Baidu API key, keep ~/.openclaw/openclaw.json private and out of source control, restrict local file access where possible, and monitor Baidu usage or billing.

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
87% confidence
Finding
The skill declares runtime requirements that include an environment variable for an API key and performs web search, implying network and secret access, but it does not explicitly declare corresponding permissions. This creates a transparency and policy-enforcement gap: a host may permit the skill without clearly surfacing that it can exfiltrate queries or misuse secrets, especially if permission gating relies on declared capabilities.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The document instructs users to place a live API credential directly into a local JSON configuration file in plaintext, but provides no warning about protecting the file, restricting permissions, avoiding commits, or using a secret store. This increases the chance of credential exposure through backups, source control, shared machines, logs, or local compromise, especially because the skill is explicitly telling users where to persist the secret.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.