Security audit

Prototype Generator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent prototype generator that inspects project structure and creates admin/list UI files, with no evidence of hidden execution, credential access, persistence, or exfiltration.

Install this if you want an assistant to generate prototype admin/list pages in a project. Review the generated files before committing them, especially when it edits existing mock UI files, and note that the packaged instructions are mainly Chinese and reference a standalone-template file that is not included in the artifact.

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
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 (2)

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The trigger conditions are broad enough to activate on generic requests about prototypes, list pages, or admin pages without strong scoping to a specific framework, repo context, or user confirmation. This can cause the skill to run in unintended contexts, scan project files, and generate or modify multiple files, increasing the chance of incorrect code changes or overbroad actions.

Natural-Language Policy Violations

Medium

Confidence: 90% confidence
Finding: The instructions, examples, and trigger phrases are all Chinese, which effectively constrains use to a specific language without an explicit user opt-in. The file does not state that the skill is intentionally limited to a Chinese-language or region-specific environment.

Static analysis

No suspicious patterns detected.