Security audit

Personal Hygiene

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple personal hygiene tracker that stores relevant routine details in one disclosed workspace file, with no code execution or hidden data movement found.

Install this only if you want the assistant to remember grooming, skincare, dental, haircut, and product details in knowledge/personal/hygiene.md. Review or delete that file if you do not want those personal routines retained, and be aware the documentation is primarily Russian.

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

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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: 95% confidence
Finding: The README’s natural-language interface is entirely Russian, including the command phrases users must issue. This can violate a language/locale policy when the skill forces a specific language without documenting user opt-in or offering alternatives.

Vague Triggers

Medium

Confidence: 96% confidence
Finding: The trigger list is very broad and includes many common words like 'skin', 'teeth', 'shower', and 'cream', which can cause the skill to activate in conversations that are only loosely related to hygiene. Unintended invocation is risky here because the skill is authorized to read and update a persistent personal-data file, so accidental activation can lead to inappropriate collection or modification of sensitive user information.

Natural-Language Policy Violations

Medium

Confidence: 87% confidence
Finding: The operational instructions and role definition are written entirely in Russian, directing the assistant's behavior in a single language. The file does not indicate that the user can choose another language or that the language restriction is required for a region-specific purpose.

Missing User Warnings

Medium

Confidence: 97% confidence
Finding: The skill instructs the agent to update `knowledge/personal/hygiene.md` whenever the user shares new information, but it does not require informing the user that personal care, health-adjacent, and routine data will be stored. This creates a privacy and consent issue because users may reveal sensitive habits or medical-adjacent details without realizing they are being persisted and reused later.

Static analysis

No suspicious patterns detected.