Back to skill

Security audit

Love Chat

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Markdown relationship-advice skill with no executable code, but users should be careful about sharing private chat logs or using manipulative dating tactics.

Before installing, consider that this skill may handle intimate or third-party chat content. Redact names, contact details, and sensitive information before asking for analysis, and avoid using it for coercion, harassment, stalking, or pressure after someone has declined interest.

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
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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill explicitly offers to analyze chat records but does not warn users about the privacy sensitivity of sharing messages that may contain personal data, intimate details, or third-party content. This creates a meaningful risk of over-collection and mishandling of private communications, especially because users may paste logs involving someone who has not consented to analysis.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The invocation examples are broad and open-ended, which can cause the skill to trigger on loosely related requests and process sensitive romantic or interpersonal content without clear scope limits. In a persuasion-oriented skill, vague boundaries increase the chance of unsafe advice generation, including manipulation, harassment, or analysis of private conversations outside the user's intended consent context.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.