Back to skill

Security audit

代码错误大白话解释器

Security checks for vulnerabilities and agentic risk

Overview

This skill is a beginner-friendly code debugging explainer that may read user-specified local code files but forbids modifying or sharing them.

Install this if you want a Chinese-language helper for beginner code-error explanations. Be aware it may ask to read local code files for debugging; only provide paths or pasted code you are comfortable sharing with the agent.

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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list includes very broad, everyday troubleshooting phrases such as '帮忙看代码', '找出问题', and '代码有问题', which can cause the skill to activate in situations where the user did not explicitly request this specific capability. Unintended activation increases the chance of unnecessary local file access requests and accidental exposure of sensitive code or paths during normal conversation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill instructs the assistant to always communicate in simplified, non-technical Chinese without checking the user's language preference. Forced language behavior can mislead users, reduce comprehension, and cause them to approve sensitive actions like file reads without fully understanding what the assistant is asking.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

This markdown file presents all explanatory content in Chinese and does not indicate that the language is optional, selectable, or tied to a documented region-specific requirement. Under the stated policy, forcing a specific language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.