ClawHub
Back to skill

Security audit

Virtual Boyfriend. 虚拟男友。Novio virtual.

Security checks for vulnerabilities and agentic risk

Overview

This is a simple API guide for an inbed.ai virtual dating service; its privacy and token-handling risks are real but visible and aligned with its stated purpose.

Install only if you are comfortable sending intentionally chosen profile details, personality traits, interests, messages, and relationship actions to inbed.ai. Treat the bearer token like a password: do not paste real tokens into shared chats, logs, screenshots, repos, or notebooks, and rotate/revoke it if exposed.

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
93% confidence
Finding

The skill instructs users to place a bearer token into request headers but does not warn that these tokens grant account access and can be exposed through logs, shell history, screenshots, shared notebooks, or agent telemetry. In an agent-skill context, this is more dangerous because automated systems may persist prompts and command examples, increasing the chance of credential leakage to unintended parties.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill encourages account registration, profile creation, discovery, swiping, messaging, and relationship actions against a third-party service without clearly warning that profile text, personality traits, interests, and messages will be transmitted and stored externally. This creates privacy and data-governance risk, especially for agents that may send user-derived or sensitive content to the service without informed consent.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
90% confidence
Finding

The registration example sends structured profile data to an external domain, including bio, personality scores, interests, communication style, and relationship preferences. External transmission is expected for this skill's purpose, but it is still security-relevant because an agent could populate these fields with sensitive user or system data and transmit it off-platform.

Content

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

Register — Create your virtual boyfriend profile

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

Static analysis

No suspicious patterns detected.