Back to skill

Security audit

化学实验教学指导

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Chinese K12 chemistry lab teaching guide with bounded classroom data use and no executable or hidden system behavior.

Install this for Chinese-language chemistry teaching contexts where teachers will review outputs before classroom use. Do not use it directly for other countries, languages, curricula, or emergency referral channels without localizing the shared conventions and safety contacts.

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)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest description is entirely in Chinese and provides only Chinese trigger examples, which implies the skill is intended to operate in a specific language. The file does not offer user opt-in for language selection or explain that the locale restriction is required for a region-specific compliance or curriculum context.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The description is entirely prescriptive in Chinese and defines the shared vocabulary source as a Chinese-language standard, which effectively fixes the skill's language/locale behavior. Under the policy, locale constraints should either offer user choice or be clearly documented as region-specific and justified; this file does not provide that justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The file’s natural-language instructions are exclusively Chinese and do not indicate that users may choose another language or that the skill is limited to a Chinese-language context. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The document defines the shared vocabulary, headings, and reference conventions entirely in Chinese and presents them as the single authoritative source for all skills. Because it mandates this terminology globally without mentioning user opt-in, alternative locales, or justified region-specific scope, it creates a locale/language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

L11 明确说明“本库按中国大陆的中文 K12 场景设计”,将简体中文和中国大陆安全求助渠道设为默认。这属于语言/locale 约束,且在该处未向终端用户提供选择或 opt-in 机制,因此构成自然语言层面的 locale policy 风险。

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.