Back to skill

Security audit

skill-lesson-kit

Security checks for vulnerabilities and agentic risk

Overview

This skill generates Chinese course review and homework Markdown files, and its file-writing behavior is disclosed and limited to that purpose.

Before installing, expect this skill to create two course-material Markdown files in the active workspace when used for Agent Skill homework or review. Check filenames before accepting output if your workspace contains existing similarly named files.

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 (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The trigger conditions are broad and include common educational phrases like '复习', '出作业', and '练习题' tied to a wide topic area, without explicit exclusion conditions or a requirement to confirm the user's intent. This can cause the skill to activate in contexts where the user did not actually want file-generating behavior, increasing the chance of unintended actions or over-broad handling.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The workflow explicitly instructs the agent to write two files into the current workspace, but it does not require user confirmation, preview, or any warning before modifying the workspace. In an agent setting, implicit file writes can lead to unintended persistence, overwrite risks, and surprising side effects even if the content itself is benign educational material.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

This markdown reference forces a specific language for all readers through its natural-language instructions and examples. Under the policy, locale or language constraints should either provide user choice or be explicitly justified as region-specific; neither is present here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The entire skill specification is written to produce materials in Chinese and does not mention adapting to the user's preferred language. This can violate language-choice policy when a skill forces a locale or language without opt-in.

Content

No source excerpt is available for this finding.