Back to skill

Security audit

主题配色工厂

Security checks for vulnerabilities and agentic risk

Overview

This is a simple theme-design skill that provides color and font recommendations, with no executable code or hidden data access.

Install this if you want Chinese-language help choosing professional color palettes and fonts. Be aware that vague requests like asking to beautify something may activate it, so use explicit wording when you want content editing rather than visual theme advice.

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
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill description and trigger examples are entirely written as Chinese-only user utterances, and the later interaction templates also assume Chinese-language responses. There is no indication that the user may choose another language or that the skill is intentionally limited to a Chinese-only context.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill description uses very broad trigger phrases such as '换个配色', '美化这个文档', and '选个专业的字体', which can match many ordinary user requests without clearly constraining scope. This can cause the skill to activate in contexts where the user did not intend a theme transformation, leading to overreach, unintended modification suggestions, or interference with other more appropriate skills.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The '立即触发' section defines ambiguous activation conditions like '帮我美化一下' and requests related to PPT or reports needing a nice theme, without requiring specific confirmation that the user wants this skill. Such broad activation logic increases the chance of accidental invocation and inappropriate handling of general editing tasks that are not strictly about theming.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.