Back to skill

Security audit

Essential Skills Package

Security checks for vulnerabilities and agentic risk

Overview

This is a broad Chinese-language productivity skill with automation examples, but the inspected artifact contains no hidden code, exfiltration, destructive behavior, or automatic execution.

Install only if you want a broad Chinese-language helper for research, coding, and automation. Before using its automation features, explicitly review file targets, requested commands, cron schedules, frequency, and removal steps.

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 (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill is defined as a very broad 'core skills package' covering research, development, and automation without clear boundaries for when it should be invoked. Overbroad skills can be activated inappropriately for high-impact tasks, increasing the chance that risky actions are taken without task-specific safeguards or review.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The skill advertises file-processing and workflow automation capabilities but does not warn that such actions may modify user data, consume resources, or affect system state. In a skill that positions itself as immediately usable, omission of these warnings can lead to unsafe execution assumptions and unintended changes.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The scheduled-task example shows how to add a cron job without warning that it creates a persistent automated action on the system. Persistence increases risk because a mistaken or abusive job can continue running after the original interaction, leading to repeated changes, data exposure, or resource abuse.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The closing guidance encourages users to 'choose your task type' and implies the skill should be used as a general entry point for many activities. This generic activation model bypasses clear constraints, making it more likely the agent will apply automation or development actions in contexts where ordinary assistance or explicit confirmation would be safer.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The description, headings, and usage guidance are all written in Chinese, and the file does not indicate that this language choice is optional or region-specific. Per the stated policy, forcing a specific language without user opt-in can be a natural-language policy issue.

Content

No source excerpt is available for this finding.