ClawHub
Back to skill

Security audit

快速配置新的agent

Security checks across malware telemetry and agentic risk

Overview

This skill appears to do the advertised Feishu bot setup, but it stores the bot secret locally and restarts the OpenClaw Gateway.

Install or run this only if you are comfortable giving it a Feishu App ID/App Secret and allowing it to modify live OpenClaw configuration. Review the account ID, agent binding, routing mode, and DM policy first; expect a brief gateway restart; protect or delete backups if they contain secrets.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Context-Inappropriate Capability

Medium
Confidence
88% confidence
Finding
The skill is presented as a configuration helper, but it also performs side-effecting system operations by invoking `openclaw config set ...` and `openclaw gateway restart` automatically. This is dangerous because running the skill changes global runtime state beyond simple file editing, which can disrupt service availability or alter behavior unexpectedly, especially when users may not anticipate command execution from a config-management tool.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The CLI persists sensitive credentials (`appSecret`) and routing changes directly into the main configuration, then attempts to change session scope and restart the gateway without any interactive confirmation or staged review. This increases the risk of accidental misconfiguration, unintended credential exposure in persistent files, and immediate service disruption from automatic restarts.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

Detected: suspicious.dangerous_exec

Shell command execution detected (child_process).

Critical
Code
suspicious.dangerous_exec
Location
index.js:169