Security audit

英语学习助手

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language English learning skill with local study tracking and no executable code or external data transfer behavior found.

Before installing, confirm you are comfortable with a Chinese-language learning workflow and with WorkBuddy storing study progress locally. Use explicit requests when invoking it to avoid accidental routing from ordinary translation or English-related conversations, and keep any voice recordings local unless you intentionally choose to share them.

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

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (15)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The README uses very broad trigger examples such as '帮我背单词', '翻译这个句子', and '制定学习计划', along with a description that activates on general English-learning topics. In an agent ecosystem, vague activation boundaries can cause the skill to trigger unintentionally during ordinary conversation, leading to prompt hijacking opportunities, incorrect routing, or inappropriate access to local learning/memory features when the user did not explicitly intend to invoke this skill.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 82% confidence
Finding: The README presents the skill entirely in Chinese and all usage examples assume Chinese-language prompts, while describing a general English-learning assistant rather than a China-specific tool. There is no indication that users may choose their preferred language or locale, which can violate language-choice policy expectations.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The README encourages invocation with very broad phrases such as any topic related to learning English, which can cause the skill to activate in situations the user did not explicitly intend. In a multi-skill environment this may route unrelated conversations into this skill, creating confusion, reduced reliability, or accidental exposure of user-provided study content to the wrong skill context.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The trigger description is broad enough to activate on many common user requests such as translation, reading, or English-related discussion, which can cause unintended routing to this skill. Over-broad activation is dangerous because it may override more appropriate skills, expose user learning data to the wrong workflow, or increase the chance that imported/exported features are invoked in contexts the user did not intend.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The documentation presents the skill entirely in Chinese and does not offer a user-language choice, which can force interactions into a language the user did not request. This is primarily a safety and usability issue: users may misunderstand instructions, data handling, or corrections, leading to accidental consent or incorrect learning actions rather than a direct technical compromise.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: SQP-3 covers natural-language policy violations such as forcing a specific language without user opt-in. This file delivers all instructions in Chinese and explicitly tells the user to reply with Chinese phrases ("我完成了" or "我有问题") without indicating that another language is acceptable.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The manifest description contains very broad activation topics such as 英语学习, 翻译, 英语阅读, and related common phrases that can match ordinary conversation outside a clear opt-in context. This can cause over-triggering of the skill, routing unrelated user content into the skill and increasing the chance of unintended handling of user text or bypass of user expectations.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The manifest fixes the skill language to zh-CN while the skill handles English-learning tasks that may involve multilingual users and mixed-language inputs. Without documented locale justification or user choice, users may be routed into a language configuration that does not match their preferences, causing misinterpretation, incorrect activation, or degraded safety and usability controls.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: This markdown skill content forces a specific language/locale for all users, which matches the policy category for language or locale violations. There is no indication that users can opt into Chinese or that the content is intentionally limited to a Chinese-only regional audience.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: This markdown file presents the entire skill content in Chinese, including the title '英语语法参考手册' and all explanatory text, with no indication that users may select another language. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is clearly justified.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill content is entirely in Chinese and is explicitly designed for Chinese-speaking English learners, which effectively forces a specific language/locale without confirming the user's preference. This can degrade usability, cause misunderstanding, or exclude users who invoke the skill through broad English-learning intents but do not read Chinese; however, it does not create direct code-execution or data-exfiltration risk.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The skill explicitly tells the user to record their voice, which creates a privacy concern because voice recordings are biometric and potentially sensitive data. While the content appears educational and does not instruct uploading or sharing the recording, the lack of any privacy notice, local-only guidance, or consent reminder makes this a real but low-severity issue.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 90% confidence
Finding: This markdown file presents all headings and instructions in Chinese, and it does not indicate that users may choose another language. Under the policy criteria, forcing a specific language without user opt-in can be 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: 78% confidence
Finding: This markdown file presents all instructional content in a single forced language/locale, which can be a natural-language policy concern when no user opt-in or justification is provided. The content does not mention that Chinese is optional, user-selected, or required for a region-specific audience.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 89% confidence
Finding: This markdown file presents all headings, organizational text, and learning guidance in Chinese, which imposes a specific language/locale on users. The policy allows locale-specific content only when the choice is offered or the constraint is clearly documented and justified, neither of which appears here.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.