Back to skill

Security audit

飞书任务管理增强版

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Feishu task-management guide, with some broad activation wording that users should treat carefully.

Install this if you want Feishu task-management help, but review prompts before allowing it to create, update, complete, or comment on tasks, especially when your request uses broad task-related wording.

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
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 conditions are broad enough to match common everyday language such as '任务', '待办', '清单', and 'task', which can cause the skill to activate in contexts the user did not intend. This increases the chance of inappropriate tool invocation and unintended task operations, especially because the skill supports state-changing actions like creating, updating, and completing tasks.

Content

No source excerpt is available for this finding.