ClawHub

Lark Multi Agent Factory

Security checks across malware telemetry and agentic risk

Overview

This skill does what it advertises: it locally configures OpenClaw Lark agents and stores required Feishu credentials in OpenClaw config, with no evidence of hidden exfiltration or destructive behavior.

Install only if you want this helper to modify local OpenClaw configuration, create agent directories, store Feishu/Lark app secrets in ~/.openclaw/openclaw.json, and potentially adjust inter-agent/session settings. Use --dry-run first and review the config changes before restarting the gateway.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding
The skill instructs the agent to read and write local OpenClaw configuration and execute shell commands, but it does not declare corresponding permissions. That creates a capability/permission mismatch: users and the platform cannot clearly see that invoking this skill can modify local state, restart services, and persist credentials. In this context the risk is elevated because the workflow writes Feishu secrets into local config and can restart the gateway.

Vague Triggers

Medium
Confidence
77% confidence
Finding
The trigger phrases are broad enough to match ordinary requests about adding or configuring an agent, which can cause the skill to activate unexpectedly. Because this skill performs sensitive local configuration actions and handles app secrets, accidental activation could lead to unnecessary credential collection or unintended system changes.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill asks users to provide a Feishu App Secret during conversation, but the collection flow does not clearly warn at that point that the secret will be stored persistently in ~/.openclaw/openclaw.json. Users may disclose sensitive credentials without understanding retention, storage location, or local exposure risks. The later '安全说明' helps, but it is separated from the credential prompt and is not a sufficiently explicit just-in-time warning.

VirusTotal

67/67 vendors flagged this skill as clean.

View on VirusTotal