Back to skill

Security audit

Feishu Task Suite

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Feishu task-management guide, with some caution needed because it can change shared tasks and task lists.

Install only if you want Codex to manage Feishu tasks. Before creating, completing, deleting, assigning, or sharing tasks, confirm the target task/list and any people or groups being added, because these changes may affect shared workflows and send notifications.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger condition is overly broad because it activates on generic words like '任务', '待办', 'to-do', '清单', and 'task' without requiring clear user intent to manage Feishu tasks. This can cause the agent to invoke the skill in unrelated contexts, leading to unintended task operations, especially because the skill supports create, update, and delete actions affecting real user data and potentially other users.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill lacks an explicit warning that assigning members or followers and modifying shared tasklists can notify or affect other users. In this context, the danger is higher because the skill explicitly supports assigning arbitrary members, adding followers automatically, and modifying collaborative task resources under a user access token, so a user may unknowingly trigger actions with social or workflow impact on others.

Content

No source excerpt is available for this finding.