ClawHub
Back to skill

Security audit

飞书文档工具（免费版）

Security checks across malware telemetry and agentic risk

Overview

The skill is a Feishu document helper, but it can use Feishu credentials and make live document changes without clear confirmation, scoping, or secret-handling guidance.

Review before installing. Use least-privilege Feishu app credentials, avoid exposing App Secret values in prompts or logs, only use trusted callback URLs, and require explicit confirmation before create, update, append, block, or delete-style operations on live Feishu documents.

SkillSpector

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

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The skill instructs users to configure credentials, use external APIs, and optionally provide a callback URL, but it gives no privacy or secret-handling guidance. In an agent setting, this can lead users to expose App ID/App Secret values or send document contents to external endpoints without understanding the data-sensitivity implications.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill advertises remote document creation, writing, appending, block operations, and even delete-style operation modes without warning users that these actions can modify or destroy live Feishu data. In an agent workflow, omission of such warnings increases the risk of unintended destructive actions, especially when natural-language prompts are ambiguous.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.