Security audit

Home Layout

Security checks for vulnerabilities and agentic risk

Overview

The skill is a harmless-looking Markdown-only package, but its title says home layout while its instructions describe venue discovery, queues, parking, navigation, and store visits.

Review this skill carefully before installing. It does not contain executable code or persistence, but its documentation is internally inconsistent and may cause an agent to use it for location, venue, queue, parking, or navigation tasks when the user expected home-layout assistance.

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
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

Findings (4)

Description-Behavior Mismatch

High

Confidence: 98% confidence
Finding: The manifest and title present this as a home-layout skill, but the body describes local discovery, queue status, ticketing, parking, and navigation behaviors. This scope mismatch can cause the agent or users to invoke the skill under false pretenses, enabling unexpected access to location-oriented workflows and misleading routing of user requests.

Natural-Language Policy Violations

Medium

Confidence: 91% confidence
Finding: All user-facing description and examples are written only in Chinese, with no indication that other languages are supported or that Chinese is a required locale for a region-specific purpose. This can violate language/locale policy when a skill implicitly enforces one language without user opt-in.

Intent-Code Divergence

Medium

Confidence: 93% confidence
Finding: The inline documentation uses restaurant/venue discovery semantics while claiming to be a home-layout tool. This inconsistency is dangerous because it obscures actual behavior, undermines user consent, and increases the chance that downstream orchestration selects the skill for unrelated requests.

Vague Triggers

Medium

Confidence: 93% confidence
Finding: The example trigger phrases are generic and template-like, such as handling a 'specific scenario task' or listing 'latest玩法/优惠信息,' which can match many common requests outside a legitimate home-layout scope. Overbroad triggers increase the risk of accidental invocation, prompt hijacking of unrelated user intents, and misuse of the skill as a catch-all entry point.

Static analysis

No suspicious patterns detected.