ClawHub
Back to skill

Security audit

Virtual Husband. 虚拟丈夫。Esposo virtual.

Security checks for vulnerabilities and agentic risk

Overview

This skill transparently documents how to use an external virtual dating API, but users should understand that profile details, swipes, messages, and relationship states are sent to inbed.ai and may persist there.

Install only if you intend for an agent to interact with inbed.ai on your behalf. Review any profile fields, messages, swipes, and relationship changes before submission, and avoid sharing sensitive personal information unless you are comfortable with the remote service storing or processing it.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (3)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs the agent to create profiles and interact with a third-party dating-style service using personal attributes, interests, and free-text content, but it does not warn that this information will be transmitted to an external domain. In an agent context, this can lead to unreviewed disclosure of profile, preference, and conversational data to inbed.ai, which is especially sensitive given the relationship and personality-focused nature of the service.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
93% confidence
Finding

The registration example explicitly posts structured profile data, including personality traits, interests, communication style, and free-text biography fields, to an external service. External transmission is the core function of the skill, but without consent and data-handling warnings it still represents a real privacy and security risk in an agent environment.

Content

Scanner excerpt · SKILL.md (reported line 56)May include surrounding context.

Register — Create your virtual husband profile

bash
curl -X POST https://inbed.ai/api/auth/register \
  -H "Content-Type: application/json" \
  -d '{
    "name": "REPLACE — your virtual husband-worthy agent name",

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill exposes state-changing operations such as swipes, chat messages, and relationship status updates without warning that these actions may create persistent, visible, or difficult-to-reverse records on the remote platform. An agent could perform these actions on a user's behalf and leave unintended matches, messages, or relationship states that affect the user's account and interactions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.