ClawHub
Back to skill

Security audit

Multi-agent-bot-feishu

Security checks across malware telemetry and agentic risk

Overview

This is a manual OpenClaw setup guide for routing Feishu bots to separate agents, with expected but sensitive credential and configuration steps.

Before installing, confirm the intended package name, back up ~/.openclaw/openclaw.json, use a dedicated least-privilege Feishu bot, prefer allowlists, restrict access to the config file, and redact appSecret values from chats, logs, screenshots, and support requests.

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
90% confidence
Finding
The skill instructs users to place Feishu bot credentials, including an app secret, into a persistent user config file but does not warn about secret handling, file permissions, redaction, or avoiding accidental disclosure in chats/logs/screenshots. In an agent skill context, this omission can lead to credential leakage and unauthorized bot control if users paste secrets into unsafe places or store them with overly broad access.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.