ClawHub
Back to skill

Security audit

Marriage

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only marriage guidance skill with clear safety and professional-referral boundaries, though one divorce section could repeat abuse-safety warnings more prominently.

Before installing, understand that this skill can help structure relationship conversations but should not replace a licensed therapist, lawyer, domestic violence advocate, or emergency services. Users facing abuse, threats, coercive control, stalking, or fear for physical safety should prioritize safety resources and professional help over standard relationship frameworks.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

This guidance explicitly says a person does not need abuse to justify leaving, but it never adds a parallel safety warning for readers who are experiencing abuse, coercive control, or credible threats. In a relationship-advice skill about divorce consideration, that omission is risky because vulnerable users may interpret the framework as applicable to unsafe situations and delay urgent safety planning, crisis support, or legal protection.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.