ClawHub
Back to skill

Security audit

Feishu Image Sender 飞书发图指南

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Feishu messaging helper, with the main caution that broad trigger phrases could start a send workflow unintentionally.

Install only if you want Codex to help send Feishu messages and upload media as a bot. Because the skill can be triggered by broad wording, review targets, attachments, and message content before allowing outbound sends in shared or business chats.

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
94% confidence
Finding

The activation list mixes specific Feishu/media terms with generic phrases like '发送图片' and '飞书消息', which are common in normal user conversation and can cause the skill to trigger when the user did not intend to invoke this specific capability. Unintended invocation is security-relevant because it can route user input into message-sending operations, increasing the chance of accidental outbound actions or misuse of connected messaging permissions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.