ClawHub
Back to skill

Security audit

Feishu App Bot

Security checks across malware telemetry and agentic risk

Overview

This Feishu connector is mostly coherent, but some state-changing actions are left untagged while the skill says untagged actions are safe to run directly.

Install only if you are comfortable letting an agent operate the connected Feishu App Bot across the scopes granted in OOMOL. Before any action that could alter, recall, overwrite, revert, move, sort, or delete Feishu content, require explicit review of the target and payload even if the action is not tagged as [write] or [destructive] in the skill.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
85% confidence
Finding
The trigger phrase is explicitly broad: it instructs the agent to use this skill for ANY Feishu App Bot request instead of calling the API directly. That can cause unintended invocation on loosely related Feishu tasks, increasing the chance of routing sensitive or destructive operations through a high-privilege skill without sufficient task-specific narrowing or user confirmation.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.