Feishu Multi-Bot

Security checks across malware telemetry and agentic risk

Overview

This skill appears to be a legitimate Feishu/Lark multi-bot configuration helper, with a real but manageable secret-handling caution.

Install/use is reasonable if you need Feishu multi-bot routing. Treat AppSecrets carefully: run the helper only in a private shell, avoid saving commands with real secrets in history, review the generated JSON before merging it into ~/.openclaw/openclaw.json, and keep Feishu app permissions limited to what the bots need.

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
98% confidence
Finding
The script requires Feishu AppSecret values to be passed as command-line arguments and then prints those secrets back into generated JSON output. Command-line arguments may be exposed through shell history, process listings, CI logs, or terminal scrollback, so this creates a real credential disclosure risk even though the script's purpose is configuration generation.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal