ClawHub
Back to skill

Security audit

China IM Workflow CLI

Security checks for vulnerabilities and agentic risk

Overview

This skill is coherent and not malware, but it teaches an agent to send, broadcast, and create business items across multiple enterprise messaging platforms without strong confirmation boundaries.

Review exact platform, tenant/account, recipients, audience size, and message content before using this skill. Treat broadcasts, customer-group messages, urgent DING sends, task synchronization, calendar invites, and document writes as actions that should require explicit confirmation before execution.

SkillSpector

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
Confidence
90% confidence
Finding
The skill advertises many broad trigger phrases such as generic IM workflow automation and cross-platform notification terms, which can cause the skill to activate for loosely related requests. In an agent setting, unintended invocation can lead to message sending, task creation, or notification workflows being proposed or executed in the wrong context across multiple enterprise platforms.

Static analysis

No suspicious patterns detected.