Security audit

Personal Love

Security checks for vulnerabilities and agentic risk

Overview

This relationship assistant is coherent, but it may automatically save very sensitive romantic details and can trigger on broad relationship keywords.

Install only if you are comfortable with the agent keeping a local relationship memory file. Review or clear knowledge/personal/love.md regularly, avoid sharing details you do not want persisted, and prefer explicit commands before saving sensitive relationship facts.

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

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (5)

Missing User Warnings

High

Confidence: 98% confidence
Finding: The skill explicitly instructs the agent to persist sensitive relationship information, including partner identity, relationship status, emotional events, and important dates, to a knowledge file without any notice, consent, minimization, or retention controls. This is dangerous because intimate personal data could be stored unexpectedly, creating privacy harm, potential cross-session exposure, and long-term accumulation of highly sensitive information.

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The README explicitly states that sensitive relationship data will be stored in a workspace file, but it does not warn users about the privacy implications or obtain meaningful consent. Because this skill handles intimate personal details, dates, and partner information, undocumented local persistence increases the risk of unintended disclosure to other tools, users of the same workspace, backups, or logs.

Vague Triggers

Medium

Confidence: 95% confidence
Finding: The trigger conditions are broad enough to activate on many ordinary conversations containing common relationship-related terms, which can cause the skill to engage unexpectedly. In this skill’s context, unexpected activation is more dangerous because it handles highly sensitive romantic and relationship data and is instructed to read and update a persistent personal memory file.

Natural-Language Policy Violations

Medium

Confidence: 91% confidence
Finding: The skill title and instructions are written in Russian and define the assistant's role in Russian, indicating a fixed language experience. The file does not state that language is optional, user-selected, or required for a region-specific purpose, which makes this a language/locale policy concern.

Natural-Language Policy Violations

Low

Confidence: 78% confidence
Finding: All user-facing instructions and commands in the file are presented exclusively in Russian. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale limitation is documented and justified.

Static analysis

No suspicious patterns detected.