design-taste 中文版

• Outcome: Pass
• Latest audit: Oct 18, 2026 · 6:59 AM UTC
• Version: 1.1.0

Overview

This skill is a coherent design review/build helper; its network and file use are disclosed and aligned with reviewing user-provided sites, images, and UI projects.

Install only if you want a design-focused assistant that may inspect your UI source, local images, or user-provided URLs. Be careful with private/internal URLs because the review script will load pages and assets in a headless browser and save screenshots/metrics locally.

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

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• MCP Least Privilege: Underdeclared Capability, Wildcard Permission, Missing Permission Declaration
• MCP Tool Poisoning: Hidden Instructions, Unicode Deception, Parameter Description Injection
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration

Findings (25)

Anti-Refusal Statement

High

• Category: Anti-Refusal
• Confidence: 85% confidence

Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · scripts/review_image.py (reported line 22)May include surrounding context.

python

Pure Pillow + numpy (uses OpenCV only if already installed). No network access.
Metrics are proxies: they catch blur, clipping, muddy palettes, crowded or off-balance
layouts. They do NOT judge meaning, emotion, or AI artifacts — the agent must look at the image.
"""
import argparse, colorsys, json, math, os, sys

Undeclared Tool Scope

Medium

• Category: MCP Least Privilege
• Confidence: 95% confidence

Finding

The skill explicitly instructs use of network-capable review tooling such as review_site.py against user-supplied URLs, but it does not declare a scoped permission model (permissions or allowed-tools). That creates an authorization gap where an agent may perform outbound requests more broadly than intended, increasing the risk of unintended browsing, SSRF-style access to internal URLs, or fetching hostile content.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 95% confidence

Finding

The trigger list includes many generic phrases like redesign, theme, poster, website review, and image critique terms that are common in ordinary conversations. Overbroad activation increases the chance the skill is invoked when the user did not intend it, which can cause unnecessary tool use, unintended file or URL processing, and execution of the skill's stronger behavioral instructions in unrelated contexts.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

• Category: Not specified by scanner
• Confidence: 92% confidence

Finding

The skill sets Chinese as the default reporting language unless the user explicitly passes --lang en, which can override or mis-handle a user's actual language preference. This is primarily a safety and usability issue: misunderstood outputs can lead users to approve actions or interpret findings incorrectly, especially when reports drive further tool use or design changes.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

• Category: Not specified by scanner
• Confidence: 95% confidence

Finding

This file presents all instructions in Chinese and does not indicate that the user can choose another language or that the skill is intentionally limited to a Chinese-speaking context. Under the policy rule for natural-language violations, forcing a specific language without user opt-in is a reportable issue.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

• Category: Not specified by scanner
• Confidence: 92% confidence

Finding

The file's natural-language instructions, headings, and report format are all in Chinese, which effectively forces a specific language for users of the skill. The policy allows language constraints only when the skill offers user choice or clearly documents a justified locale-specific purpose, neither of which appears here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

• Category: Not specified by scanner
• Confidence: 88% confidence

Finding

该文件标题及全文内容均以中文撰写，未说明这是面向特定中文用户群体的区域性文档，也未提供语言选择或英文替代。根据规则，强制单一语言且无用户 opt-in 或明确业务理由，属于自然语言层面的语言/地区政策风险。

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 presents all instructions and evaluation criteria exclusively in Chinese. Under the policy, forcing a specific language without offering a choice or documenting a justified locale constraint 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: 86% confidence

Finding

The entire skill file is written only in Chinese and provides no indication that language selection is optional or constrained to a Chinese-only context. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 95% confidence

Finding

The mode table includes broad trigger phrases such as generic requests for review, beautification, redesign, theming, or critique that can overlap with ordinary user speech. In an agent-routing context, this can cause unintended invocation of the design skill, leading the system to load unnecessary references, run review scripts, or produce actions outside the user's intended scope.

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 contains natural-language guidance exclusively in Chinese, and there is no indication that users may choose another language or that the content is intentionally region- or locale-specific. Under the policy for natural-language violations, forcing a specific language without user opt-in can be a policy issue.

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 skill file is written in Chinese and provides no indication that the user 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 restriction is explicitly justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

• Category: Not specified by scanner
• Confidence: 97% confidence

Finding

This CSV contains substantial Chinese-language text in the comment column alongside English in comment_en, but the file does not document any language-selection mechanism or justify a Chinese locale constraint. For a generally scoped skill asset, embedding natural-language content that forces a specific language can violate the language/locale policy when no user choice or documented regional scope is provided.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

• Category: Not specified by scanner
• Confidence: 94% confidence

Finding

The script sets LANG = "zh" by default and T() uses that global to select all user-facing output language. This imposes a specific locale on users without opt-in, which matches the language/locale policy violation criteria for all file types.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium

• Category: Not specified by scanner
• Confidence: 96% confidence

Finding

The documentation explicitly states 'The script never downloads anything itself.' However, the implementation uses Playwright to open remote URLs via page.goto and waits for page/network loading, which necessarily causes the browser context to fetch HTML and associated assets. This is an active contradiction in intent/documentation, not merely an omitted detail.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

• Category: Not specified by scanner
• Confidence: 95% confidence

Finding

The browser context is explicitly created with locale="en-US", which imposes a specific locale on every reviewed site. This is a natural-language policy concern because it forces a locale choice rather than offering the user a choice or clearly limiting the tool to a justified region-specific use case.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

• Category: Not specified by scanner
• Confidence: 95% confidence

Finding

The mobile browser context likewise hard-codes locale="en-US" for all captures. This repeats the same locale-policy issue in a second execution path and may affect site language, consent banners, pricing, and content shown to the user.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

• Category: Not specified by scanner
• Confidence: 78% confidence

Finding

The final reporting instruction says to write using the skill's language variant, which can conflict with the user's language and create ambiguous prioritization. While not directly enabling code execution or data access, it can degrade informed consent and accuracy by presenting conclusions in a language the user did not request.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

• Category: Not specified by scanner
• Confidence: 82% confidence

Finding

This manifest-like JSON includes prompts and expected outputs in both English and Chinese, but it does not indicate that language selection is user-driven or optional. Under the policy rule, forcing or assuming a specific language/locale without opt-in can be a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

• Category: Not specified by scanner
• Confidence: 86% confidence

Finding

The document states that the generated report defaults to a Chinese template, with English available only via an explicit flag. This creates a default language constraint that may conflict with organizational language-choice policies when no user preference has been established.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

• Category: Not specified by scanner
• Confidence: 79% confidence

Finding

The report format instruction specifies --lang zh|en, which constrains output to Chinese or English only. This is a natural-language locale restriction, and the file does not indicate user opt-in beyond those two choices or justify the limitation as region-specific.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

• Category: Not specified by scanner
• Confidence: 88% confidence

Finding

This markdown file contains natural-language guidance that steers users toward English as the default prompt language. Under the language/locale policy, forcing or strongly defaulting to a specific language without user opt-in can be a policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

• Category: Not specified by scanner
• Confidence: 78% confidence

Finding

All natural-language instructions and trigger descriptions in this file are Chinese-only, and there is no indication that users may choose another language or that the locale restriction is intentional and documented. This can constitute a language policy issue if the skill is expected to serve users without forcing a specific language by default.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

• Category: Not specified by scanner
• Confidence: 95% confidence

Finding

The file’s natural-language instructions are exclusively in Chinese, and there is no indication that users may opt into another language or that the skill is intentionally limited to a Chinese-speaking context. This can violate language/locale policy expectations when skills are expected to be usable without forcing a specific language.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

• Category: Not specified by scanner
• Confidence: 90% confidence

Finding

Line L44 gives locale-specific guidance for a Chinese interface, but the document does not indicate that language or locale selection is optional or user-driven. This can be read as prescribing a specific locale treatment without explicit opt-in, which matches the language/locale policy check.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.