ClawHub
Back to skill

Security audit

OpenClaw飞书任务管理

Security checks for vulnerabilities and agentic risk

Overview

This Feishu task skill is a straightforward task-management guide with disclosed, purpose-aligned read and write actions, though its activation wording is broader than ideal.

Install this if you want an agent to operate on Feishu task data. Be aware that the trigger wording is broad, so users should be explicit when they want task changes and should review any create, update, delete, completion, or membership action before it is sent to Feishu.

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
95% confidence
Finding

The trigger condition is broad enough to activate on common mentions like '任务', '待办', 'to-do', or 'task', even when the user may only be discussing tasks conversationally rather than requesting tool use. This can cause unintended invocation of a task-management skill that performs read/write operations on user task data, increasing the risk of inappropriate actions or privacy-impacting context switches.

Content

No source excerpt is available for this finding.