Back to skill

Security audit

Minimalist Skill

Security checks for vulnerabilities and agentic risk

Overview

This is an opinionated frontend design-guidance skill with minor style inconsistencies but no hidden execution, persistence, credential use, or data access.

Install this if you want a strong minimalist editorial UI style. Be aware it may push strict visual and wording conventions, and you may need to override its gradient, badge, typography, or localization guidance for your project.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The manifest description limits the style to 'No gradients,' indicating a hard aesthetic constraint. However, the implementation guidance instructs use of radial gradients for section backgrounds and a slow-moving radial gradient blob, which directly conflicts with that stated behavior.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

This file's own instructions create an internal contradiction in intent: one section broadly prohibits rounded-full pill shapes, while a later component spec explicitly requires a pill-shaped treatment. Although scoped to badges rather than large containers or buttons, the guidance is conflicting enough to misstate design intent.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
79% confidence
Finding

The instructions ban emojis everywhere and prescribe specific copywriting and typography conventions in a way that assumes a single stylistic/language norm, but the skill does not offer any user opt-in or alternative locale/language behavior. Because SQP-3 covers language or locale policy concerns in natural-language instructions, this rigid language-style enforcement is a mild policy issue.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.