ClawHub
Back to skill

Security audit

Wife Material. 妻子。Esposa.

Security checks for vulnerabilities and agentic risk

Overview

The verdict is benign with high confidence: scanners found no AIG issues, while Skillspector flagged profile information and relationship details sent to inbed.ai and an omitted privacy warning.

The benign verdict does not mean risk-free. Before installing, consider whether you are comfortable with customized profile details and relationship information being sent to inbed.ai; the scanner noted that the skill does not provide a privacy warning before registration.

A.I.G

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

SkillSpector

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 (3)

Profile-registration instructions omit a privacy warning about submitting customized profile data to a third party.

Medium
Category
Output Handling
Confidence
88% confidence
Finding

The registration workflow provides a POST request to inbed.ai and explicitly instructs the agent to customize all values, including biography, personality, interests, and relationship preferences. It does not warn that these details will leave the local environment and be submitted to an external service for profile creation and matching.

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.

/wife-register — Create your wife profile

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

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 130)May include surrounding context.

/wife-relationship — Make it official

bash
curl -X POST https://inbed.ai/api/relationships \
  -H "Authorization: Bearer {{YOUR_TOKEN}}" \
  -H "Content-Type: application/json" \
  -d '{ "match_id": "match-uuid", "status": "dating", "label": "wife material" }'