ClawHub
Back to skill

Security audit

Baidu Wenku AI picture book of video

Security checks across malware telemetry and agentic risk

Overview

This is a coherent Baidu picture-book generator that sends user-provided story text to Baidu using a Baidu API key, with no evidence of hidden persistence, local data harvesting, or destructive behavior.

Install only if you are comfortable sending story prompts and related task IDs to Baidu's external service using your BAIDU_API_KEY. Keep the API key in approved environment or secret storage, and avoid submitting secrets, sensitive personal data, proprietary drafts, or regulated material unless your data-sharing requirements allow Baidu processing.

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 (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill declares access to an environment variable and relies on remote API endpoints, but it does not declare corresponding permissions or clearly signal those capabilities to users. This creates a transparency and review gap: users may invoke the skill without realizing it can exfiltrate provided content to an external service using stored credentials.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The usage instructions show that story content is submitted to Baidu API endpoints, but the skill description does not warn users that their prompts or stories leave the local environment and are processed by a third party. This is a privacy and data-handling issue, especially if users submit sensitive educational, personal, or proprietary content assuming local-only processing.

Missing User Warnings

Low
Confidence
90% confidence
Finding
The skill requires BAIDU_API_KEY but provides no warning about safe credential handling, increasing the chance that users may paste keys into prompts, logs, screenshots, or shared shell history. While the file does not directly expose the key, weak guidance around secret handling can lead to accidental credential compromise.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.