ClawHub
Back to skill

Security audit

Baidu Search 1

Security checks across malware telemetry and agentic risk

Overview

This skill appears to do what it advertises: perform Baidu web searches using a user-provided Baidu API key.

Install only if you are comfortable sending search queries to Baidu and using a Baidu Cloud API key. Prefer a dedicated, revocable key, protect ~/.openclaw/openclaw.json with restrictive file permissions, avoid syncing or sharing that config file, and verify the listing identity because the bundled metadata does not exactly match the registry metadata.

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
88% confidence
Finding
The skill requires access to an environment variable containing an API key and performs outbound network requests, but the manifest does not declare explicit permissions for those capabilities. This creates a governance and transparency gap: users or platforms may not realize the skill can exfiltrate secrets or communicate externally, making review and policy enforcement weaker even if the intended functionality is legitimate web search.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The guide instructs users to place a live API key directly into `~/.openclaw/openclaw.json` without warning that the credential will be stored in plaintext on disk. This increases the chance of accidental disclosure through local compromise, backups, dotfile syncing, screenshots, or file sharing, especially because the document normalizes direct secret embedding as the expected setup path.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.