ClawHub
Back to skill

Security audit

Baidu Wenku AIPPT

Security checks across malware telemetry and agentic risk

Overview

This skill appears to be a straightforward Baidu AI PPT generator that sends the user's presentation content to Baidu as part of its stated function.

Install only if you are comfortable sending presentation prompts and any supplied web content to Baidu for processing. Avoid using it with confidential, regulated, or proprietary material unless Baidu's terms and your organization's policy allow it, and keep the BAIDU_API_KEY scoped and protected.

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 (4)

Lp3

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding
The skill invokes Python scripts, requires an API key in the environment, and is designed to make outbound API requests, but the manifest does not explicitly declare corresponding permissions. This creates a transparency and policy-enforcement gap: an agent or platform may allow execution without clearly informing users that the skill can access secrets, run shell commands, and contact external services.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The script sends user-supplied query text and optional web_content directly to Baidu's external AI PPT service without any consent prompt, redaction, or clear warning to the user at the point of transmission. In a skill context, users may provide sensitive business, personal, or proprietary content expecting local processing, so silent exfiltration to a third party creates a real confidentiality and privacy risk.

External Transmission

Medium
Category
Data Exfiltration
Content
outline = ""
    chat_id = ""
    query_id = ""
    with requests.post(URL_PREFIX + "generate_outline", headers=headers, json=params, stream=True) as response:
        for line in response.iter_lines():
            line = line.decode('utf-8')
            if line and line.startswith("data:"):
Confidence
88% confidence
Finding
requests.post(URL_PREFIX + "generate_outline", headers=headers, json=

External Transmission

Medium
Category
Data Exfiltration
Content
"web_content": web_content,
        "enable_save_bos": True,
    }
    with requests.post(URL_PREFIX + "generate_ppt_by_outline", headers=headers, json=params, stream=True) as response:
        if response.status_code != 200:
            print(f"request failed, status code is {response.status_code}, error message is {response.text}")
            return []
Confidence
94% confidence
Finding
requests.post(URL_PREFIX + "generate_ppt_by_outline", headers=headers, json=

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.