word-knowledge-map

• Outcome: Pass
• Latest audit: Sep 18, 2026 · 3:34 AM UTC
• Version: 0.1.0

Overview

This skill coherently creates Chinese-language English vocabulary learning posters and does not show hidden execution, credential access, persistence, or destructive behavior.

Install this if you want Chinese-language English vocabulary knowledge-map posters. Be aware that its activation rule is broad and its language is not configurable, so it may be inconvenient in non-Chinese workflows or casual prompts containing English words.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (16)

Ae1

High

• Category: analysis-evasion

Content

/infographic-prompt.md`、`templates/style-guide.md`、`templates/layout-modes.md`、`references/style-target-care.png`、`examples/care.json`

• Confidence: 100% confidence
• Finding: Referenced artifact was not completely inspected

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: The activation condition is overly broad: "输入英文单词时使用" can match many normal conversations containing an English word, causing the skill to trigger outside the user's intent. This can hijack unrelated requests, create incorrect outputs, and interfere with other tools or safer instruction paths, especially because the skill enforces a multi-step pipeline once activated.

Natural-Language Policy Violations

Medium

• Confidence: 95% confidence
• Finding: The skill description hard-codes Chinese-language behavior without user choice or a clear locale restriction. If auto-invoked for users operating in another language, it can produce unexpected language switching, reduce comprehension, and override user preferences, which is especially risky when combined with the broad trigger condition.

Natural-Language Policy Violations

Medium

• Confidence: 89% confidence
• Finding: This JSON skill content is entirely structured around Chinese explanations, translations, and audience targeting, including a Chinese-only audience field at L004 and Chinese instructional text throughout. Because the file does not offer a language choice or document a justified region-specific constraint, it presents a natural-language locale policy concern.

Rp1

Medium

• Category: MCP Rug Pull
• Confidence: 70% confidence
• Finding: npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Rp1

Medium

• Category: MCP Rug Pull
• Confidence: 70% confidence
• Finding: npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Natural-Language Policy Violations

Medium

• Confidence: 93% confidence
• Finding: The instructions require Chinese content and formatting, including Chinese titles and smaller Chinese text, which imposes a specific language/locale. Under the policy, forcing a language without user opt-in is a natural-language policy violation unless the constraint is explicitly justified or optional.

Natural-Language Policy Violations

Medium

• Confidence: 95% confidence
• Finding: The schema requires every example to include a "chinese" field alongside "english", which embeds a fixed locale/language requirement into the skill data model. For a general knowledge schema, this is a natural-language policy concern because it forces one language choice rather than allowing user selection or documenting a region-specific purpose.

Natural-Language Policy Violations

Medium

• Confidence: 95% confidence
• Finding: Line L03 states that the filtering stage 'must produce' `layout_plan` and the surrounding document is written entirely in Chinese, with line L60 also constraining user-facing terminology. This indicates a fixed language/locale expectation without user opt-in, which can violate language policy for general-purpose skills.

Natural-Language Policy Violations

Medium

• Confidence: 88% confidence
• Finding: The document explicitly requires English to be larger and bold while also requiring Chinese lines in examples, which imposes a fixed bilingual output format. Because the file does not indicate user opt-in or that the skill is limited to a Chinese-language educational context, this is a natural-language locale policy concern.

Natural-Language Policy Violations

Low

• Confidence: 85% confidence
• Finding: This JSON content presents meanings, explanations, and audience information in Chinese throughout the file. Under the natural-language policy rule, forcing a specific language without user opt-in can be a locale-policy issue when no alternative language choice or justification is provided.

Natural-Language Policy Violations

Low

• Confidence: 88% confidence
• Finding: This JSON skill file is entirely structured for a Chinese-language learning context, including a Chinese-only audience label at L004 and Chinese translations/explanations throughout. Because SQP-3 applies to all file types, this can be treated as a locale/language constraint that is not accompanied by any explicit user choice or justification in the file.

Natural-Language Policy Violations

Low

• Confidence: 85% confidence
• Finding: This JSON file contains natural-language strings in Chinese for the "chain" fields, but there is no accompanying indication that the skill is intentionally Chinese-only or that users can opt into this locale. Under the policy for natural-language violations, forcing a specific language without user choice can be a locale-policy issue.

Natural-Language Policy Violations

Low

• Confidence: 81% confidence
• Finding: This manifest-style JSON is in scope for policy checks, and it specifies a Chinese audience at L004 while the instructional fields throughout the file present explanations and translations only in Chinese. That can be a language/locale policy concern because the file does not indicate user opt-in, alternative locale support, or a documented region-specific justification.

Natural-Language Policy Violations

Low

• Confidence: 88% confidence
• Finding: This JSON skill content presents explanations, translations, and teaching guidance entirely in Chinese, indicating a fixed language/locale assumption. Under the policy rule, forcing a specific language without user opt-in is a natural-language policy concern unless the locale restriction is clearly documented and justified.

Natural-Language Policy Violations

Low

• Confidence: 93% confidence
• Finding: This markdown file contains substantial Chinese-only instructional and evaluative text alongside English, which can effectively force a language/locale on users who may not understand it. The file does not state that the skill is region-specific or provide any opt-in or alternative language choice.

Static analysis

No suspicious patterns detected.