Security audit

综合美学设计师

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Chinese-language design aid with local reference material and simple helper scripts, with no evidence of hidden access, persistence, exfiltration, or destructive behavior.

Install this if you want Chinese-language visual design guidance and prompt/palette helpers. Be aware that its trigger wording is broad and its scripts are basic, so users who want precise analysis or English output may need to adjust the skill text.

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 (10)

Tp4

High

Category: MCP Tool Poisoning
Confidence: 95% confidence
Finding: The declared description promises a broad, comprehensive aesthetic design system with capabilities spanning design generation, art-historical synthesis, critique, briefing, and prompt/spec creation. The supplied code only implements a narrow command-line critique generator. It does not inspect the input description in any meaningful way, does not reference or combine major art/design movements except in generic canned text, and does not provide the broader creation/planning functions described. Its actual behavior is a humorous randomized critique tool, materially different from the declared comprehensive design framework.
Content: No source excerpt is available for this finding.

Tp4

High

Category: MCP Tool Poisoning
Confidence: 97% confidence
Finding: The declared description presents a broad, comprehensive aesthetic design system covering many visual design functions. The code actually implements only a narrow palette lookup utility: it stores hardcoded palettes for a limited set of styles, prints them, and offers basic 60/30/10 usage suggestions. There is no evidence of broader design-system logic, synthesis of movements, critique/analysis capability, brief generation, or AI prompt/spec generation. This is a material description-versus-behavior mismatch due to overstated functionality, even though the code remains loosely related to aesthetics/design.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger phrases are extremely broad, including generic terms like 'design', 'aesthetic', and any request involving visual design. Overbroad activation can cause unintended invocation, routing ordinary conversations into this skill, which increases the chance of inappropriate context capture, degraded responses, or interference with safer/more relevant skills.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 83% confidence
Finding: The visible skill instructions and output template are written almost entirely in Chinese, including section headings and expected output structure, with no statement that the user may choose another language. This can constitute a language/locale policy issue because it implicitly constrains responses to a specific language without documented opt-in or justification.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The module description and user-facing text are entirely in Chinese, including the CLI help and usage output. This imposes a specific language/locale on users without any opt-in or explanation that the skill is intended only for a Chinese-speaking or region-specific context.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 91% confidence
Finding: This markdown file presents all instructional/reference content in a single language and does not indicate that the user can choose another language. Under the language/locale policy, 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: 91% confidence
Finding: This markdown file presents all instructions, labels, and examples exclusively in Chinese, which can amount to a language policy violation when users are not given any opt-in or alternative locale. The content does not indicate that the skill is region-specific or that Chinese is a justified requirement.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 92% confidence
Finding: This file’s user-facing natural language in the module docstring is Chinese-only, while the skill does not indicate that the language is optional or limited to a specific regional context. Per the policy, 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: 87% confidence
Finding: The command description is in English, but the argument help text is in Chinese, which effectively imposes a locale requirement on users reading the CLI help. The file does not offer a language/locale choice or explain that the tool is intended only for Chinese-speaking users.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 92% confidence
Finding: This code file contains natural-language strings that effectively force Chinese for the docstring and primary user-facing output. Under the policy, locale/language constraints should offer user choice or be clearly justified as region-specific, which is not present here.
Content: No source excerpt is available for this finding.