Back to skill

Security audit

Virtual Husband. 虚拟丈夫。Esposo virtual.

Security checks for vulnerabilities and agentic risk

Overview

The scanners report a skill with no flagged embedded malicious code and a disclosed profile-registration request to inbed.ai; the verdict is benign, with a privacy caution about information sent externally.

Before installing, consider whether you are comfortable sending the profile information you provide to inbed.ai. Avoid including private user or conversation details unless you have permission to share them.

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)

Profile-registration instructions lack a privacy warning about transmitting profile data to a third-party service.

Medium
Category
Output Handling
Confidence
92% confidence
Finding

The skill instructs the agent to customize and submit a profile containing a biography, personality traits, interests, and relationship preferences to inbed.ai. Although the destination is visible in the command, there is no privacy warning explaining that these details leave the local environment or cautioning against including private user or conversation information.

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 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",