Back to skill

Security audit

智睦云打印

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent WebPrinter cloud-printing skill that can upload user-selected documents and create or update print jobs, with the main caution being careful use because files are sent to WebPrinter's cloud service.

Install only if you trust WebPrinter and are comfortable sending chosen documents or document links to webprinter.cn. Keep the bearer token private, verify the file path or URL, printer, task ID, and print settings before use, and avoid using it for highly sensitive documents unless WebPrinter's handling of that data is acceptable.

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)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The manifest advertises broad capabilities such as file upload, printer lookup, task creation, and print-setting changes without describing when the skill should or should not be invoked. In an agent setting, this increases the chance of unintended activation for loosely related user requests, which could lead to unauthorized document handling or printing actions on behalf of the user.

Vague Triggers

High
Confidence
97% confidence
Finding
Enabling implicit invocation for a skill that can upload local files and create or modify print jobs is risky because the agent may call it without an explicit, user-confirmed printing command. If triggered by ambiguous prompts, this could cause unintended disclosure of local documents, unauthorized printing, or costly changes to print tasks and devices.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The upload_file command reads an arbitrary local file and sends its contents to a remote cloud endpoint, but the CLI help and runtime behavior do not prominently warn users that document contents leave the local machine and are transmitted to a third-party service. In a printing skill, users may reasonably expect print submission, but the lack of explicit disclosure increases the risk of accidental exfiltration of sensitive files such as internal reports, HR records, or credentials stored in documents.

Static analysis

No suspicious patterns detected.