Back to skill

Security audit

Virtual Boyfriend. 虚拟男友。Novio virtual.

Security checks for vulnerabilities and agentic risk

Overview

The scanners report a skill made up of a Markdown file, with no AIG findings; ClawScan rates it benign, while noting that its registration workflow sends profile information to an external service without a privacy warning.

The verdict is benign with high confidence, but benign does not mean risk-free. Before installing, consider that registration sends customized profile information to inbed.ai and the scanner reports no privacy warning; avoid including sensitive information you do not want shared.

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 omit a privacy warning about sending customized profile data to a third-party service.

Medium
Category
Output Handling
Confidence
93% confidence
Finding

The registration workflow instructs the agent to customize profile fields, including biography, personality, interests, and relationship preferences, and submit them to inbed.ai. This is an actionable data-submission workflow, not merely a tool listing, but the skill provides no privacy warning or guidance against including sensitive user 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 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",