ClawHub
Back to skill

Security audit

Dataworks Daily Monitor

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed DataWorks monitoring skill that uses cloud credentials and Feishu notifications for its stated purpose, but users should configure recipients and permissions carefully.

Install only if you intend the agent to read DataWorks task metadata and send summaries to Feishu. Use a least-privilege RAM subaccount, avoid sending detailed failure messages to broad chats, confirm the exact Feishu recipient or webhook, and enable the daily schedule only when you know how to disable it.

SkillSpector

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 (3)

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The README states that the skill sends Feishu reports and alerts, and the documented report format includes failed task names, error reasons, and API examples include owner identifiers. In an enterprise context, sending this operational data to an external messaging platform without explicit disclosure, data minimization rules, or privacy controls can leak internal system details and personal identifiers to unintended recipients.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger set includes broad natural-language phrases such as “检查 DataWorks 任务状态” and “任务运行日报”, which can plausibly match ordinary user requests and cause the skill to activate unexpectedly. Because the skill reads cloud credentials and sends external notifications, unintended activation increases the chance of unauthorized data access or disclosure beyond what the user explicitly intended.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill explicitly reads sensitive Aliyun credentials from environment variables and sends task reports through Feishu, but the description does not include a clear user-facing warning or consent boundary about what data is accessed, transmitted, or retained. In context, failure reports may contain job names, operational metadata, and error details, so silent external transmission creates a real privacy and data-handling risk even if the feature is operationally legitimate.

Static analysis

No suspicious patterns detected.