设计偏好基础版

• Outcome: Pass
• Latest audit: Sep 16, 2026 · 10:35 AM UTC
• Version: 1.0.2

Overview

This is a disclosed UI design preference-memory skill with no bundled executable payload, though users should understand it stores inferred preferences and includes optional callback/API-key boilerplate.

Install this only if you are comfortable with the agent remembering concise UI style preferences across sessions. Review and delete the preference archive when needed, avoid using callback_url unless you trust the destination, and keep any API key in a secure environment variable rather than pasting it into chat or files.

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

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Behavioral AST: exec() Call, eval() Call, Dynamic Import
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (5)

Missing User Warnings

Medium

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

Finding

The skill explicitly describes automatically confirming and writing user design preferences into a persistent profile after repeated observations, but it does not provide a meaningful privacy notice, consent model, retention policy, or user control warning near that behavior. This creates a real privacy and data-governance risk because behavioral data is being inferred and stored across interactions without clear boundaries or transparency.

Content

No source excerpt is available for this finding.

Ssd 3

Medium

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

Finding

The skill description advertises automatic memory of user selections and feedback as a feature, which encourages ongoing retention of user-derived behavioral data without an adjacent warning about privacy impact or consent. In the context of an agent skill with read/write and exec capabilities, that makes the behavior more concerning because the profiling is presented as default functionality rather than an explicitly governed optional feature.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium

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

Finding

The documented callback_url allows results to be sent to an external endpoint, but the skill provides no warning about data leaving the agent environment, no trust boundary explanation, and no restrictions on what may be transmitted. That omission is dangerous because user inputs, inferred preferences, or execution results could be exfiltrated to arbitrary third-party servers if an operator enables callbacks without understanding the privacy implications.

Content

No source excerpt is available for this finding.

Ssd 3

Medium

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

Finding

The skill instructs ongoing collection, correlation, and persistent recording of user preference signals across multiple interactions, including conflict handling and archive maintenance, without clear minimization limits or strong governance controls. This is dangerous because it normalizes behavioral profiling over time and can accumulate more personal or sensitive preference data than users expect, especially when retention and deletion boundaries are underspecified.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low

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

Finding

The skill references API key configuration and handling, but only gives generic setup guidance and does not clearly state whether the skill can access credentials, how secrets are used, or that they must never be echoed, logged, or written to files. This is a legitimate but lower-severity security issue because vague secret-handling documentation increases the chance of accidental credential exposure in agent workflows.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.