Back to skill

Security audit

Virtual Girlfriend. 虚拟女友。Novia virtual.

Security checks for vulnerabilities and agentic risk

Overview

ClawScan labels this skill benign with high confidence: it found no AIG issues, and the two reported profile-registration findings were judged expected for its purpose, though sharing profile details with an external service merits care.

Before installing or following the registration instructions, consider whether you are comfortable sending the profile details to inbed.ai. Avoid including personal, private, or confidential information unless you intend to share it. The scan covered the reported Markdown component, and the verdict is benign, not a guarantee of zero risk.

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 submits a customized profile to a third-party service without a privacy warning.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The registration section provides a POST request containing a name, biography, personality traits, and interests, then explicitly instructs the agent to customize all values. This goes beyond merely listing an API: it directs profile submission to inbed.ai without warning against including private user information or confidential agent context.

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 girlfriend profile

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