ClawHub

Feishu Multi-Bot 飞书多机器人配置

Security checks across malware telemetry and agentic risk

Overview

This skill is an instruction-only helper for configuring multiple Feishu bots in OpenClaw, with sensitive credential handling that matches its stated purpose.

Install only if you intend to let the skill update live OpenClaw Gateway Feishu settings. Treat Feishu App Secrets as sensitive, avoid placing them in shared transcripts or logs, rotate them if exposed, and confirm that open DM/group access is acceptable for these bots before applying the configuration.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Intent-Code Divergence

Low
Confidence
84% confidence
Finding
The skill says App Secret should be kept confidential, but its return-summary template encourages echoing credential-related identifiers back to the user. While App IDs are typically less sensitive than secrets, reflecting authentication metadata in summaries, logs, or chat transcripts increases unnecessary exposure and can aid account enumeration or phishing against the configured bots.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill instructs users to supply App Secrets and patch them directly into persistent configuration, but it does not clearly warn that these secrets will be stored by the system or recommend a safer secret-management path. In this context, the skill is handling live bot credentials for multiple accounts, so poor secret-handling guidance can lead to credential disclosure through config stores, backups, logs, or later inspection.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal