Back to skill

Security audit

Feishu Task Manager

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward Feishu task-management skill with disclosed task and comment read/write behavior, but users should handle the Feishu App Secret carefully.

Install only with a Feishu app whose permissions are limited to the task features you need. Store the App Secret in a protected config or secret store, do not paste real secrets into chats or repositories, and review any create, complete, or comment action before allowing the agent to make workspace changes.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Session Persistence

Medium
Category
Rogue Agent
Content
### 3. Use

```
"Create a task to review the launch plan, due Friday"
```

## 📖 Examples
Confidence
80% confidence
Finding
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Session Persistence

Medium
Category
Rogue Agent
Content
| Create task | `Create task "Review PR" assigned to @zhang, due tomorrow` |
| List today | `Show my tasks due today` |
| Complete | `Mark task #123 as done` |
| Team task | `Create task for each team member to update status` |

## 🔧 Technical Info
Confidence
80% confidence
Finding
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill advertises task creation, modification, completion, comments, and checklist management, but it does not clearly warn users that invoking it can perform write actions in their Feishu workspace. This increases the risk of users authorizing or triggering unintended state-changing operations without informed consent, especially in agentic workflows where natural-language prompts may be ambiguous.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The documentation instructs users to obtain and configure an App Secret but provides no guidance on secure handling of that credential. Secrets embedded in configs, prompts, logs, screenshots, or repositories can be stolen and then used to access or abuse the Feishu application and its task permissions.

Session Persistence

Medium
Category
Rogue Agent
Content
### Example 1: Quick Task Creation

Human: Create a task for me to review the Q4 report, due Friday

Agent: (uses feishu_task_tool to create the task)
Confidence
80% confidence
Finding
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Static analysis

No suspicious patterns detected.