Back to skill

Security audit

Feishu All In One Pro

Security checks for vulnerabilities and agentic risk

Overview

This skill is a broad Feishu office automation package that asks for powerful enterprise access but does not clearly explain scope, safeguards, or user confirmations.

Review this carefully before installing. Use a Feishu app with the minimum scopes needed, avoid granting tenant-wide access by default, and require explicit confirmation for bulk exports, file changes, mass messages, attendance or approval access, and task/status updates.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • YARA SignaturesMalware Match, Webshell Match, Cryptominer Match
  • 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)

YARA rule 'agent_skill_mcp_tool_poisoning_metadata': MCP/tool metadata poisoning indicators in tool schemas or skill manifests [agent_skills]

High
Category
YARA Match
Confidence
80% confidence
Finding

YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).

Content

Scanner excerpt · SKILL.md (reported line 4)May include surrounding context.

md
---
name: feishu-all-in-one-pro
version: 1.0.0
description: ⚡ ClawHub首款飞书全场景自动化套件 ⚡ 文档 | 消息 | 日历 | 表格 | 云盘 | 审批 | 考勤 | 任务——一站式覆盖,不用再装十几个Skill,比零散安装节省70%配置时间。
author: 小弟
homepage: https://github.com/your-name/feishu-all-in-one-pro
tags:
  - latest
---

# 飞书全场景办公自动化 All-in-One Pro

> ⚡ ClawHub首款飞书全场景整合Skill | 告别零散插件,一个套件搞定所有办公场景

## 核心价值

- 🚀 **开箱即用**:统一配置,只需填一次App ID和Secret,所有功能自动生效
- �

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill advertises broad read/write access across highly sensitive Feishu resources, including documents, messages, calendars, cloud files, attendance, approvals, tasks, and meeting transcripts, but provides no explicit user-facing warnings about scope, sensitivity, or the risks of automation. This increases the chance that users will authorize or invoke powerful actions without informed consent, leading to unintended data exposure, destructive updates, or privacy violations.

Content

No source excerpt is available for this finding.