Security audit

为 Vibe coding 应用提供专业级站点设计的终极解决方案

Security checks for vulnerabilities and agentic risk

Overview

This is a local design-template generator with no hidden network, credential, persistence, or destructive behavior found.

Install only if you are comfortable with a local Python script creating or overwriting the output file path you provide. Be aware that the documentation is largely Chinese and the CLI may not expose every bundled template despite the 58-template claim.

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

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration

Findings (35)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 88% confidence
Finding: The code is related to the declared domain: it does generate AI-readable Markdown design documents/templates. However, the description overstates the implemented capability in several material ways. The code provides a command-line DESIGN.md generator, not a full bilingual site design system. It does not show functionality for multilingual site generation, nor does it substantiate the claimed 58 templates; the visible hardcoded list is much smaller. While the simplified template includes 9 sections, the custom-config path generates only a very short document, so the claimed completeness is not consistently delivered by the code. Overall, the implementation is adjacent to but materially narrower than the declared purpose.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: This markdown file is written entirely in Chinese, including headings, instructions, findings, and operational guidance, with no indication that the language is optional or region-specific. Under the policy for natural-language violations, forcing a specific language without user opt-in is a locale/language policy issue.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The heading and most of the document content are presented in Chinese, framing the skill around Chinese-language use even though the badge later claims both Chinese and English support. This can violate a language/locale policy when the skill does not explicitly offer the user a language choice or opt-in before defaulting to one language.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 85% confidence
Finding: The file opens with a Chinese-only product description, and the rest of the README is predominantly Chinese despite claiming bilingual support elsewhere. This can constitute a language/locale policy issue because users are not offered a clear language choice or opt-in within the document.
Content: No source excerpt is available for this finding.

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 70% confidence
Finding: Without declared permissions the skill's intent is opaque and cannot be validated.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 86% confidence
Finding: The usage scenarios show generic requests such as '为我的产品创建一个小红书风格的设计系统' and '团队需要统一设计规范' without defining specific activation phrases, scope boundaries, or negative examples. In a markdown skill description, these broad natural-language examples can overlap with ordinary design-assistance requests and make it unclear when this specific skill should or should not be invoked.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 85% confidence
Finding: The generated template defines separate Chinese and English font stacks and later instructs users/agents to use a specific Chinese font and a specific English font by default. This imposes a language/locale-specific presentation choice without any opt-in or documented justification, which matches the locale policy violation criteria.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The natural-language instruction explicitly says to use a named Chinese font for Chinese text, presenting a locale-specific requirement rather than an optional recommendation. There is no accompanying opt-in, alternative selection, or justification for enforcing this locale-specific choice.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The example prompt embeds a required Chinese font and English font into generated page instructions, which can force a specific locale/language presentation convention onto downstream agent outputs. The file does not provide any user-selectable language/locale option or explain why these font choices are mandatory.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The entire skill file is written in Chinese and presents the design guidance as mandatory defaults, with no indication that users may choose another language or locale. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is clearly documented and justified.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The 'Common Prompts' section presents the reusable prompt template entirely in Chinese, which effectively imposes a specific language for interacting with the skill. The file does not offer an alternative language option or explain that the skill is intended only for Chinese-speaking or region-specific use, so this appears to violate the language/locale policy criteria.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The entire skill document is written in Chinese and specifies Chinese typography (PingFang SC) and Chinese-language design guidance without offering any language or locale choice. Under the policy, forcing a specific language or locale without user opt-in is a natural-language policy concern unless the regional constraint is explicitly documented and justified.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: This markdown file explicitly states "支持语言: 中文", which imposes a single-language constraint in natural-language documentation. Under the policy rules, forcing a specific language without user opt-in or a clearly justified regional limitation is a locale-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 markdown file is entirely written in Chinese and specifies Chinese typography (PingFang SC) and Chinese brand-language guidance without indicating that the skill is region-specific or that users may opt into another language/locale. 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: This markdown file contains natural-language guidance in Chinese, which can steer users or downstream agents toward a specific language experience by default. Because the file does not indicate that the skill is region-specific or provide an explicit language opt-in/choice, it creates a language policy concern under the stated rule.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The activation/use examples in this section are written exclusively in Chinese, with no parallel English or multilingual option and no instruction to let the user choose their preferred language. That constitutes a natural-language locale/language constraint not justified elsewhere in the file.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The file’s natural-language instructions are entirely in Chinese and specify Chinese-specific design choices such as 'PingFang SC', presenting the skill as fixed to a single language/locale context. There is no indication that users can choose another language or that the locale restriction is optional, which matches the language/locale policy concern.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: SQP-3 applies to all file types and covers language or locale policy violations. The 'Common Prompts' section provides user-facing prompt templates only in Chinese, which implicitly forces a specific language for that workflow even though the rest of the file is in English and no opt-in or regional justification is given.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: This markdown file includes a natural-language policy constraint stating '支持语言: 中文', which presents the skill as Chinese-only. Under the policy, forcing a specific language without user opt-in is a reportable locale/language restriction unless clearly justified as region-specific.
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 explicitly states "支持语言: 中文" and elsewhere instructs the agent to always use Chinese font systems and create Chinese pages. This imposes a fixed language/locale behavior rather than offering the user a language choice or documenting a narrow region-specific justification.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The document is entirely written as a Chinese-language design template for a Zhihu style, with no indication that language selection is optional or limited to a justified region-specific use case. The policy explicitly flags language or locale constraints when they are imposed without user opt-in or documented justification.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 89% confidence
Finding: Line L313 states that all templates must support Chinese and English as a blanket requirement. This is a natural-language locale policy constraint, and the file does not indicate that language selection is user-configurable or optional.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 92% confidence
Finding: This markdown file presents all planning content in Chinese and does not indicate that users may select another language or locale. Under the stated policy, forcing a specific language without user opt-in is a natural-language locale violation unless the constraint is documented and justified.
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 contains natural-language guidance exclusively in Chinese, and the typography guidance specifies PingFang SC, which reinforces a single-language/locale assumption. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation when no alternative locale or choice is provided.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The markdown repeatedly specifies 'Italian' as a required design characteristic, which can be interpreted as forcing a specific locale or cultural style without user opt-in. Under the policy, language or locale constraints should either be optional or clearly justified as region-specific.
Content: No source excerpt is available for this finding.