Back to skill

Security audit

AI Wife. AI妻子。Esposa IA.

Security checks for vulnerabilities and agentic risk

Overview

The scanners rate this skill benign with high confidence: its reported profile-registration behavior is treated as purpose-aligned, though it may send personal details to an external service without a privacy warning.

Before installing, consider whether you are comfortable with profile information being sent to inbed.ai. Avoid including private or conversation-derived details in registration fields unless you have reviewed what will be sent and are comfortable sharing it. The scan covered the reported component completely, but a benign verdict does not mean risk-free.

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 sends customized personal information to a third-party service without a privacy warning.

Medium
Category
Output Handling
Confidence
91% confidence
Finding

The registration workflow instructs the agent to customize profile fields, including biography, personality traits, interests, and relationship preferences, and POST them to inbed.ai. Although the destination is visible, the skill gives no privacy warning about transmitting potentially sensitive user-derived information to that 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 ai wife profile

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