ClawHub
Back to skill

Security audit

Feishu Doc Batch Export

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly a straightforward Feishu document exporter, but it overstates batch features and asks users to grant Feishu read authority that the included script does not fully need or implement.

Review before installing. Use a dedicated low-privilege Feishu app, avoid granting drive-wide read access unless you actually need and verify folder export support, and export into a deliberate local directory because document contents and images will be saved there. Expect the included script to handle single docx links, not the advertised batch/folder workflow.

SkillSpector

Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding
The skill explicitly instructs use of environment variables, network access to Feishu APIs, and writing exported Markdown and images to disk, yet it does not declare permissions or safety boundaries. This creates a transparency and consent problem: an agent or user may invoke filesystem and network-capable behavior without an explicit permission model, increasing the risk of unintended data export or overwriting local files.

Missing User Warnings

Low
Confidence
84% confidence
Finding
The skill mentions exporting to local Markdown and downloading images, but it does not prominently warn that it will write potentially many files to the local filesystem. In agent-driven environments, insufficient disclosure can lead to accidental persistence of sensitive document contents on disk, unexpected storage consumption, or writes into unsafe locations.

Static analysis

No suspicious patterns detected.