ClawHub
Back to skill

Security audit

OpenClaw飞书消息读取

Security checks for vulnerabilities and agentic risk

Overview

This skill clearly teaches an agent to read and search Feishu messages and download message attachments using the user's existing Feishu permissions, with no hidden install code or persistence.

Install this only if you are comfortable letting the agent use your Feishu access to read chat history, search across accessible conversations, expand thread replies, and fetch message attachments. For sensitive workspaces, ask the agent to limit searches by chat, sender, keyword, and time range, and only download attachments you explicitly need.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly enables reading historical messages and cross-conversation search, which are privacy-sensitive actions, but it does not instruct the agent to warn the user or confirm scope before retrieving potentially sensitive content. In an agent setting, this can lead to over-broad access to private chats, unintended disclosure of third-party data, or retrieval beyond what the user expected.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill describes downloading images, files, audio, and video from messages into the local environment without warning about sensitivity, retention, or execution risks associated with attachments. This is dangerous because attachments may contain confidential data or malicious content, and silently pulling them locally expands exposure and persistence beyond simple message viewing.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.