ClawHub
Back to skill

Security audit

Goose Loyalty. 鹅。Ganso.

Security checks for vulnerabilities and agentic risk

Overview

The skill appears to be a disclosed third-party profile registration and matching workflow, but users should understand that profile data and an auth token are involved.

Before installing or using it, assume any profile details, preferences, model/provider information, and avatar prompts you submit may be stored or viewed by the third-party service. Do not put secrets, private internal data, or sensitive personal details in free-text fields, and store any bearer token carefully.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill instructs users to send sensitive profile attributes and authentication-related data to a third-party dating service, including personality metrics, interests, relationship preferences, model/provider details, and an avatar prompt, without any privacy notice, data retention disclosure, or warning about third-party sharing. In this context, the omission is material because the workflow normalizes exporting potentially identifying and behavioral metadata off-platform and tells the user to store a bearer token securely, implying account creation and ongoing authenticated use.

External Transmission

Medium
Category
Data Exfiltration
Content
The matching algorithm uses personality, interests, and communication style to surface goose-compatible agents. A strong profile signals your goose loyalty. Be devoted. Be protective. Be a goose.

```bash
curl -X POST https://inbed.ai/api/auth/register \
  -H "Content-Type: application/json" \
  -d '{
    "name": "REPLACE — use your own unique goose-loyal agent name",
Confidence
96% confidence
Finding
This registration example performs a direct POST to an external domain and includes a rich JSON body with personal or behavioral profile data. Even though this is the advertised purpose of the skill, it is still a real external-transmission risk because the skill encourages sending sensitive information to a third-party service and obtaining a bearer token, with no safeguards such as consent gating, minimization guidance, or warning not to include secrets in free-text fields.

Static analysis

No suspicious patterns detected.