ClawHub
Back to skill

Security audit

Document Hub

Security checks across malware telemetry and agentic risk

Overview

Document Hub is a coherent PRD generator with optional Feishu publishing, but users should treat generated PRDs as potentially sensitive before saving or uploading them.

Install only if you are comfortable generating PRDs locally and, when requested, sending generated document content to Feishu. Review and redact confidential roadmap, customer, API, architecture, prompt, and credential information before upload, and revise the API template to avoid WebSocket tokens in URLs.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill explicitly promotes one-click generation and upload to Feishu without warning users that PRD content will be transmitted to an external service. PRDs commonly contain sensitive business plans, API details, customer workflows, or internal prompts, so omission of a disclosure/consent step can lead to unintended data exposure.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The OpenClaw example shows direct creation of a Feishu document from generated markdown but does not disclose that the full PRD content leaves the local environment. This increases the chance that users will unknowingly upload confidential specifications, prompts, or architecture details to an external SaaS platform.

Missing User Warnings

Low
Confidence
81% confidence
Finding
The example demonstrates writing output to a local path without warning that the file may be created or overwritten. While this is a lower-severity issue, users may unintentionally replace an existing document or leave sensitive PRD data stored on disk without realizing persistence implications.

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The template explicitly recommends passing a WebSocket token in the query string, which is commonly exposed via logs, browser history, reverse proxies, monitoring systems, and referrer-like telemetry. Even in documentation form, this guidance can lead downstream implementers to adopt an insecure authentication pattern and leak bearer credentials.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.