ClawHub
Back to skill

Security audit

个性化英语听力训练师

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese K12 English listening practice skill whose profile use is disclosed, consent-gated, and aligned with personalization.

Installers should treat this as intended for Chinese K12 education and verify local privacy, guardian-consent, crisis-referral, and curriculum localization requirements before deploying outside that context.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (7)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The manifest description and trigger phrases are entirely written as Chinese-only user utterances, and the document consistently frames interaction in Chinese without stating that users may choose another language. This is a natural-language locale policy concern because the skill appears to require a specific language for invocation and use without explicit opt-in or documented justification.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

L003-L005 明确写明该参考资源“适用学段：小学高段与初中”，将文档定位为初中及以下训练资源。但 L525-L577 又专门加入“高中：按三大主题选材”以及高中阶段的意图与态度训练方法，和前述适用范围形成直接冲突，不只是信息遗漏。

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The entire document is written in Chinese and presents operational guidance for SKILL behavior, but it does not indicate 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 concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The file is entirely framed as mandatory operating guidance in Chinese, including required user-facing phrasing such as the one-sentence explanation in L11 and quoted prompts in L14, L34, and L35. There is no indication that the skill should adapt to the user's preferred language or obtain opt-in before enforcing this locale, which can violate language-choice policy.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

该文件的标题和整体说明均以中文呈现，属于自然语言层面的语言/locale 约束，但文档中没有提供用户可选择其他语言的说明，也没有明确声明这是仅面向中文使用者的区域性资源。按规则，未经用户选择而强制单一语言可构成语言/locale 政策问题。

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

L007-L009 声称“两个参数只有一套口径”，并将语速口径限定在小学高段到初三，且 L003 已说明不使用高中档位。可是在 L525-L567 中又给出高中部分并引用“见 SKILL 第九节”的高中规则与算法，表明文档并非只有一套统一口径。

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
94% confidence
Finding

L11 明确规定“本库按中国大陆的中文 K12 场景设计”，并指定示例、话术和求助渠道默认中国大陆。这属于自然语言中的语言/地区约束；虽然下文说明了跨地区部署需做本地化处理，但该默认限制本身仍是需要记录的 locale policy。

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.