ClawHub
Back to skill

Security audit

Feishu IM Read

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Feishu message-reading guide; it handles sensitive chat content, but the access is purpose-aligned and limited to the user's own permissions.

Install only if you want the agent to help inspect Feishu messages and attachments you can already access. For privacy, ask it to use the narrowest chat, keyword, sender, and time filters practical, and avoid downloading files or expanding threads unless needed.

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 (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill explicitly enables cross-conversation message search, thread expansion, and media/file download, which can expose sensitive chat content and attachments across multiple contexts. Although it notes that calls run as the user and are limited by that user's permissions, it does not clearly warn about privacy implications, data minimization, or the risk of retrieving more content than the user intended.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.