ClawHub
Back to skill

Security audit

Feishu Messaging 0

Security checks for vulnerabilities and agentic risk

Overview

This is a Feishu messaging helper with disclosed API examples, but users should confirm any message, image, or file before sending it.

Install this only if you intend to use a Feishu bot for messaging, chat lookup, and uploads. Confirm recipients, message contents, and exact files before sending; keep APP_ID and APP_SECRET secure; avoid debug logging sensitive responses in production. Do not rely on it for document creation unless you add or verify that workflow yourself.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)

Description-Behavior Mismatch

Medium
Confidence
94% confidence
Finding
The manifest description and usage scope emphasize sending Feishu messages, with trigger scenarios around finding chat/member IDs and retrying failed sends. However, the skill documentation also includes image upload, file upload, and an overview that says it can create documents and manage Feishu resources, which expands the behavior beyond a narrow messaging workflow.

Natural-Language Policy Violations

Medium
Confidence
95% confidence
Finding
The natural-language description, trigger examples, and usage instructions are entirely in Chinese, with no indication that other languages are supported or that Chinese is a deliberate, justified locale restriction. Under the policy, forcing a specific language without user opt-in is a reportable natural-language policy issue.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill documents APIs for sending messages and uploading images/files to Feishu without warning that user-provided text and local files may be transmitted to an external service. In an agent setting, this omission can lead to unintended exfiltration of sensitive data, especially if the agent uses local files or forwards content without clear user confirmation.

Description-Behavior Mismatch

Low
Confidence
87% confidence
Finding
The manifest says the skill supports '消息发送与文档创建工作流', and the title/overview repeat document-related functionality. But the concrete code examples only cover chat lookup, message sending, image upload, file upload, and chat member queries; no document creation API usage is shown.

Static analysis

No suspicious patterns detected.