Security audit

狗狗如厕训练

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward dog potty-training tracker with local logging; its main risk is that it stores household routine details over time.

Install only if you are comfortable storing dog-training logs locally, including walk times, room locations, accidents, and pet details. Consider reviewing or deleting memory/dog-training.md and TOOLS.md when the training period ends.

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 (4)

Natural-Language Policy Violations

Medium

Confidence: 93% confidence
Finding: The skill description, triggers, examples, and assistant responses are all written to operate in Chinese, and there is no indication that the user can opt into another language. This can violate language-choice policy when a skill effectively forces one language without documented justification or user selection.

Vague Triggers

Medium

Confidence: 90% confidence
Finding: The trigger phrases are broad enough to activate on common pet-related utterances without clearly constraining when the skill should engage. This can cause unintended invocation and collection of behavioral or household data, especially because the skill also writes persistent logs.

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The skill instructs writing training events to a persistent memory file without warning the user that information will be stored. Even if the data seems low sensitivity, it can reveal routines, home occupancy patterns, and household details over time.

Missing User Warnings

Low

Confidence: 88% confidence
Finding: The configuration section stores household and pet details such as dog name, age, routines, and purchased supplies without any privacy warning. While not highly sensitive on its own, this information can still profile the household and routines if retained or exposed.

Static analysis

No suspicious patterns detected.