Security audit

Publish Skill Final

Security checks for vulnerabilities and agentic risk

Overview

This UI design skill is mostly documentation plus an optional script that appends disclosed design rules to the current project's .cursorrules file.

Review the changes before running the optional apply_ui_rules.py script because it appends persistent design guidance to your project's .cursorrules file. The skill otherwise appears proportionate for UI design assistance and does not request sensitive credentials or broad local access.

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

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (4)

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The skill explicitly instructs users to run a script that modifies the current project's .cursorrules file, but it does not warn that a project configuration file will be changed or recommend reviewing the changes first. Because .cursorrules can influence future AI behavior across the workspace, silent or poorly explained modification creates a trust and supply-chain style risk, especially if users execute the command without inspecting the script.

Natural-Language Policy Violations

Low

Confidence: 88% confidence
Finding: Line L04 includes a fixed Indonesian phrase as part of the core philosophy, which can impose a language/locale preference in project guidance without any opt-in or contextual justification. This matches the policy category for language or locale constraints expressed in natural language.

Natural-Language Policy Violations

Low

Confidence: 79% confidence
Finding: The statement "Black on white is mandatory" is a natural-language constraint that forces a specific presentation choice with no user choice or contextual justification. Under the policy criteria, mandatory language/locale-style constraints should be avoided unless explicitly optional or justified.

Natural-Language Policy Violations

Low

Confidence: 89% confidence
Finding: Line L25 states 'Sans-serif only,' which is a natural-language requirement that forces a specific style choice. Under the policy criteria, prescriptive language constraints should either offer opt-in or be clearly justified as context-specific; this file presents it as an absolute rule.

Static analysis

No suspicious patterns detected.