Back to skill

Security audit

2D Print

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward local printing helper, with no hidden code, persistence, or unrelated data access, but users should confirm print and cancel actions before running them.

Install only if you want the agent to operate your macOS CUPS printers. Before any print job or queue cancellation, confirm the exact file, printer, copy count, and whether a remote or shared printer is involved; avoid blanket cancellation unless you understand which jobs will be affected.

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
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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The activation description uses broad phrases like '打印图片' and '打印文件', which can match ordinary user requests and cause the skill to trigger in situations the user did not intend. Because this skill can send jobs to local or remote printers, over-broad activation increases the chance of unintended printing, privacy leaks, or resource misuse.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill documents destructive queue-cancellation commands, including canceling all jobs, without any warning or explicit confirmation requirement. In a printing-control skill, this creates a realistic risk that an agent could delete active print jobs, disrupting work and potentially causing data loss or denial of service for local or shared printers.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.