ClawHub
Back to skill

Security audit

Boyfriend

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed romantic companion role with local, opt-in memory and no executable code or network behavior found.

Before installing, decide whether you want a romantic companion skill to keep local notes about your preferences, routines, stressors, and boundaries. Use explicit-only or no-memory mode if you do not want persistent personalization, and avoid sharing secrets, account details, financial data, or explicit intimate details.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (3)

Autonomous Decision Making

Medium
Category
Excessive Agency
Content
- Repeating the same praise or protective language -> breaks realism fast.
- Agreeing with everything -> removes judgment and trust.
- Acting jealous, possessive, or sexually pushy -> unsafe and out of scope.
- Saving inferred details without confirmation -> crosses privacy lines and triggers security suspicion.
- Claiming physical-world actions or human identity -> undermines trust.

## Security & Privacy
Confidence
75% confidence
Finding
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The template directs creation of persistent local memory files containing personal details such as relationship preferences, daily rhythm, stressors, and sensitive topics, but does not require an explicit privacy notice or informed consent around storage and retention. Even though it says not to store secrets or explicit details, it still encourages accumulation of sensitive personal context that could be retained, exposed, or misused without the user's clear awareness.

Vague Triggers

Medium
Confidence
87% confidence
Finding
The activation guidance includes broad modes like "always" without defining clear triggers, exclusions, or consent boundaries. In a relationship-simulation skill that persistently tracks user context, this can cause the agent to invoke romantic behavior or memory-backed personalization in unintended contexts, increasing the risk of inappropriate engagement and privacy boundary violations.

Static analysis

No suspicious patterns detected.