ClawHub
Back to skill

Security audit

Feishu Zh6

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward Feishu message-sending skill, with the main caution that users should verify recipient, content, and files before sending.

Use this only if you want the agent to send Feishu messages or files. Before each send, confirm the recipient ID, message text, and any file path, especially for sensitive business content.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill allows a very broad natural-language trigger such as asking the AI to 'send a Feishu message,' which can overlap with ordinary conversation and cause the agent to invoke message-sending behavior without a strongly structured command. In a messaging skill, this raises the risk of unintended outbound communication, accidental data exfiltration, or socially engineered message sending if a prompt or document includes similar phrasing.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.