Security audit

chore-wheel-genius

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local household chore scheduler whose file use and behavior match its stated purpose.

Reasonable to install if you want a local chore-tracking CLI. Be aware it stores household names, ages, skills, assignments, and skip reasons in plaintext at ~/.chore_wheel.json, and review age-based chore suggestions yourself before assigning chores involving cooking, tools, chemicals, pets, or childcare.

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

MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
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)

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 88% confidence
Finding: The skill describes a command-line tool that reads and writes local state (~/.chore_wheel.json) but does not declare any tool scope such as permissions or allowed-tools. That creates an authorization gap: an agent/runtime may grant broader file access than the skill actually needs, increasing the chance of unintended local file reads or writes if the skill is invoked in a more privileged environment.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The guide assigns potentially hazardous chores to minors, including cooking, bathroom cleaning, yard work, minor home repairs, babysitting, and walks with pets, but provides little or no explicit safety precautions beyond a few scattered notes such as 'with supervision' or 'with direction' for younger children. In a household-assignment tool, users may treat these recommendations as authoritative defaults, which can normalize unsafe task assignment and increase risk of injury, chemical exposure, or inadequate supervision.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The usage string says skip <member> <chore> <reason>, implying the chore and reason are distinct arguments. But the implementation sets chore = " ".join(args[1:]), so the reason text is included in the chore match, making the documented invocation fail for multiword reasons and contradicting the advertised command behavior.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Low

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The module docstring advertises assign [weeks], suggesting callers can request assignments for multiple weeks or a specified week range. The actual cmd_assign function does not read args at all and always uses week_key(0), so the documented interface contradicts the real behavior.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.