Back to skill

Security audit

化学解题教练

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese K12 chemistry tutoring skill with disclosed optional memory and reminder handoffs; it should be localized before use outside mainland China.

Install this only for the intended Chinese K12 context, or localize curriculum, consent requirements, and crisis-help contacts before use elsewhere. Confirm that profile memory, cross-skill sharing, parent visibility, and reminders remain opt-in as described.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (5)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

This crisis-referral protocol is safety-critical, but it is written only in Chinese while also containing region-specific escalation guidance. If used in a non-Chinese-speaking deployment, operators, guardians, or students may misunderstand or fail to follow self-harm and emergency-referral instructions, causing delayed or incorrect crisis response.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

This JSON schema hard-codes user-facing enum values and semantic constraints in Chinese, such as consent subjects like "学生本人" and age bands like "小学低段/初中/高中", with no indication that alternative languages or locales are supported. Under the policy for natural-language violations, forcing a specific language without user opt-in is a locale-policy issue.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

Natural-language descriptions in the schema are written entirely in Chinese, including the main note and top-level description, with no indication that language selection is optional or limited to a China-specific deployment. This can violate language/locale policy because it imposes a specific language on downstream users and maintainers without opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The entire shared guidance file is written in Chinese and includes prescriptive interaction instructions for all SKILLs, but it does not state that language selection is optional or limited to a China-specific deployment context. Under the policy, forcing a specific language or locale without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

L11 明确写明“本库按中国大陆的中文 K12 场景设计”,将语言和地域设为默认前提。虽然后文说明了其他地区部署前需做本地化处理,但这里仍构成对语言/locale 的默认强约束,而非面向用户的显式选择或 opt-in。

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.