Security audit

ym-household-chore-split

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only household chore planning skill with no hidden execution, networking, persistence, or credential use found.

Before installing, users should know this skill is mainly for Chinese-language chore scheduling and may activate on broad chore-related phrases. Avoid sharing sensitive household details unless needed for the schedule; the inspected artifact does not show networking, local file access, or persistence.

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: 90% confidence
Finding: The trigger list uses very generic everyday phrases like “家务分工”, “值日表”, and “chore chart”, which can match ordinary conversation and cause the skill to activate when the user may only be discussing chores generally. This is primarily a scope and routing issue rather than a code-execution risk, but unintended activation can lead to incorrect assistance, privacy over-collection, or interference with a more appropriate skill.

Vague Triggers

Medium

Confidence: 87% confidence
Finding: The usage conditions describe broad scenarios like complaints about unfairness or roommate chores without defining clear non-activation boundaries, increasing the chance that the skill is selected for emotional support, conflict mediation, or other adjacent requests it is not designed to handle. In context this is somewhat mitigated by the stated capability boundaries, but the ambiguity still creates a realistic risk of misrouting and overreach.

Natural-Language Policy Violations

Medium

Confidence: 93% confidence
Finding: This markdown file is entirely written in Chinese and provides reusable instructions/templates without any indication that the skill is region-specific or that users may choose another language. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Static analysis

No suspicious patterns detected.