ClawHub
Back to skill

Security audit

Feishu Parallel Dispatch

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Feishu workflow helper that spawns background child tasks for longer requests so the chat stays responsive.

Install this only if you want Feishu chats to hand longer requests to background child sessions automatically. Users should expect asynchronous follow-up messages and should explicitly ask for a synchronous answer when they do not want a task spawned.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill hardcodes Chinese acknowledgement examples as the prescribed foreground reply pattern, which can override the user's language preference and cause confusing or inappropriate responses in multilingual environments. While not a direct security exploit, it can degrade trust, create miscommunication, and violate expected interaction boundaries when the user did not opt into Chinese output.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.