ClawHub
Back to skill

Security audit

OpenClaw飞书任务管理

Security checks across malware telemetry and agentic risk

Overview

This is a coherent Feishu task-management skill with disclosed task-changing abilities, but users should be careful with broad task requests and deletions.

Install this only if you want an assistant to manage Feishu tasks. Use specific task or list names/GUIDs, and confirm before allowing deletes, assignee changes, or list membership changes, especially when your request uses generic words like task or to-do.

SkillSpector

By NVIDIA
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
92% confidence
Finding
The skill advertises invocation on very common terms like '任务', '待办', 'to-do', '清单', and 'task' without narrowing to clear user intent to manage Feishu tasks. This can cause the agent to invoke the skill in unrelated contexts, leading to unintended task creation, modification, or disclosure of task data under the user's access token.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.