ClawHub
Back to skill

Security audit

Feishu Task Control

Security checks for vulnerabilities and agentic risk

Overview

This skill gives users scoped control to list or stop background tasks in the current Feishu chat, with no hidden code, persistence, or data access found.

Install only if you want Feishu chat users to list and stop background tasks. Be aware that using stop-all or /stop may cancel in-progress work, so users should choose specific tasks when possible.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (2)

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The markdown describes the ability to inspect, stop, or clean up background tasks, including stopping all tasks, but it provides no warning that these actions may interrupt running work or terminate user processes. For markdown files, safety-relevant behavior affecting system integrity or user work should be disclosed clearly.

Natural-Language Policy Violations

Low
Confidence
77% confidence
Finding
The README includes a Chinese-only section stating the usage is consistent with the English description, but it does not indicate whether language choice is optional or user-selectable. This can be read as imposing a specific locale presentation without explicit opt-in.

Static analysis

No suspicious patterns detected.