ClawHub
Back to skill

Security audit

Feishu Doc Workflow

Security checks for vulnerabilities and agentic risk

Overview

This Feishu document workflow is openly scoped to editing and sharing documents, but users should be careful before making any document publicly readable.

Install only in an environment where the Feishu app permissions are intended for document editing and sharing. Before using the public-link workflow, confirm the document contains no sensitive, internal, personal, or confidential information and that public access is truly desired.

A.I.G

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

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)

Skill Enumeration

Medium
Category
Agent Snooping
Content
- **改正文内容** → 用 `feishu_doc` 的 `read` / `write` / `append` / `insert` / `update_block`
- **调整图片位置或补图** → 用 `feishu_doc` 的 `list_blocks` + `upload_image` + 必要时 `delete_block`
- **把文档开成互联网可读** → 走 Feishu Drive public permission 接口（见下文）
- **发送普通文件给用户**（HTML / ZIP / PDF / 代码文件）→ 不用本 skill，改看 `skills/feishu-send-file/SKILL.md`

## 推荐工作流
Confidence
80% confidence
Finding
Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill provides step-by-step instructions to make Feishu documents publicly accessible on the internet, including exact API fields to set, but does not require an explicit privacy warning or user confirmation before exposing content. This increases the risk of accidental data disclosure, especially because the workflow normalizes internet-readable sharing as a routine operation and could be applied to sensitive documents.

Static analysis

No suspicious patterns detected.