Security audit

Grid Sticker Generator

Security checks for vulnerabilities and agentic risk

Overview

This is a prompt-only sticker image generation skill with no code execution, persistence, credential access, or hidden data handling.

Installers should understand that this skill is mainly Chinese-language and defaults to a Chinese office-worker meme template unless the user gives a custom theme. Review generated images for unwanted text or background artifacts, but the inspected package does not request sensitive access or system changes.

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
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (5)

Natural-Language Policy Violations

Medium

Confidence: 81% confidence
Finding: The entire skill documentation and user-facing examples are written as Chinese-only instructions, including examples of how users should invoke the skill, but there is no indication that other languages are supported or that users may choose their preferred language. Under the policy, forcing a specific language without opt-in is a natural-language policy concern unless the locale restriction is explicit and justified.

Vague Triggers

Medium

Confidence: 87% confidence
Finding: The trigger examples are very broad and map to ordinary image-generation requests, which can cause the skill to activate unintentionally and override more appropriate agent behavior. In a multi-skill agent, this increases the risk of prompt-routing confusion, unexpected resource loading, or applying hidden defaults like the office-worker template when the user did not explicitly request them.

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: The skill body is written as a directive in Chinese and presents the generator behavior as fixed, while the manifest describes it as a universal generator. There is no indication that users may choose another language or that the Chinese-only presentation is required for a region-specific use case, which creates a locale-policy concern.

Natural-Language Policy Violations

Medium

Confidence: 86% confidence
Finding: The instruction at L94 tells the user to describe their persona as a '打工人形象' or issue a command, framing the interaction around a specific Chinese-language cultural context without offering a language or locale choice. Under the policy, locale or language constraints should either be optional or clearly justified.

Intent-Code Divergence

Low

Confidence: 92% confidence
Finding: The template's earlier visual rules require an absolutely transparent background and explicitly forbid simulated or non-transparent backgrounds. However, L80 tells the prompt builder to include 'White background' while also asking for transparent output, which is an active contradiction in the documented intent and could cause generation behavior inconsistent with the stated visual requirements.

Static analysis

No suspicious patterns detected.