ClawHub
Back to skill

Security audit

Feishu Post

Security checks across malware telemetry and agentic risk

Overview

The skill mainly sends Feishu rich-text posts as advertised, but it also includes an undocumented debug script that can read and print Feishu message data using available credentials.

Install only if you are comfortable granting this package access to Feishu credentials. Use send.js with explicit recipients, avoid passing secret or personal files to --text-file, and do not run debug_msg.js unless you intentionally want to fetch and print Feishu message data in your logs.

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 (1)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill documentation describes sending text directly to Feishu, including content loaded from a local file, but does not warn users that the full content will be transmitted to an external service. This creates a real risk of accidental disclosure of sensitive local data, especially when users pass files assuming they are processed locally or only reformatted.

VirusTotal

No VirusTotal findings

View on VirusTotal