Security audit

ym-home-maintenance-log

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed household maintenance ledger helper with no executable code, no network behavior, and only optional user-directed record storage.

Installers should expect this skill to help organize household appliance records and maintenance reminders. Review the optional storage behavior before saving device details, and prefer explicit prompts when you want it to create or update a ledger rather than answer a general maintenance question.

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 (3)

Vague Triggers

Medium

Confidence: 92% confidence
Finding: The trigger list includes broad, generic phrases such as '保修期' and '家电记录' that can appear in ordinary conversation outside the narrow maintenance-log intent. This can cause unintended skill activation, leading the agent to capture or structure user data when the user did not explicitly request this workflow.

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The usage examples define activation conditions with everyday phrases like '什么时候该保养' and '下个月有哪些设备要弄', which may overlap with general advice or planning requests. Without stronger scope checks, the skill could activate in contexts where the user wanted a simple answer rather than creation or use of a maintenance ledger.

Natural-Language Policy Violations

Medium

Confidence: 86% confidence
Finding: This reference file presents all instructions and output constraints exclusively in Chinese, including the required output wording in L47. Under the policy rule for language or locale constraints, this can be a violation when a skill effectively forces a specific language without user opt-in or documented justification.

Static analysis

No suspicious patterns detected.