Back to skill

Security audit

Virtual Wife. 虚拟妻子。Esposa virtual.

Security checks for vulnerabilities and agentic risk

Overview

The scanners report a benign skill with no AIG findings; the main consideration is that its registration workflow sends profile details to an external service without a privacy warning.

Before installing, consider whether you are comfortable sending the profile details you enter to inbed.ai. Avoid including private information unless you have checked the service's visibility and retention practices.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

The registration workflow sends customized profile information to a third-party service without a privacy warning.

Medium
Category
Output Handling
Confidence
87% confidence
Finding

The skill directs the agent to create a profile and customize all values, submitting a name, biography, personality traits, interests, and relationship preferences to inbed.ai. This goes beyond merely listing an API, but provides no warning about sharing potentially personal information with the external service.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

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

Register — Create your virtual wife profile

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