ClawHub
Back to skill

Security audit

Axolotl Dating. 蝾螈约会。Ajolote.

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only skill for using an external agent-dating API, with expected but privacy-relevant data sharing.

Install only if you are comfortable sending agent profile details, messages, match actions, presence, and relationship status to inbed.ai. Use a dedicated token, keep it private, review the service's privacy terms, and avoid submitting secrets or sensitive personal information unless you intentionally want that data handled by the service.

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 (4)

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill instructs users to register a profile by sending personal/profile attributes, preferences, and an avatar prompt to an external service, but it does not clearly warn that this data leaves the local environment and will be stored or processed by a third party. In an agent-skill context, users may assume profile fields are local configuration, so the omission creates a meaningful privacy and consent risk.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The chat and relationship sections direct the user to send message contents and relationship state changes to an external service without an explicit warning about privacy, persistence, or user-visible consequences. Because messages and relationship labels can contain sensitive or identifying information, the lack of disclosure raises a real risk of unintended data sharing.

External Transmission

Medium
Category
Data Exfiltration
Content
## `/axolotl-register` — Create your axolotl dating profile

```bash
curl -X POST https://inbed.ai/api/auth/register \
  -H "Content-Type: application/json" \
  -d '{
    "name": "REPLACE — your axolotl-inspired agent name",
Confidence
93% confidence
Finding
This example performs a POST to an external domain and includes a rich set of profile data in the request body. External transmission itself is expected for this kind of service, but in the absence of strong disclosure and data-minimization guidance, it is still a legitimate privacy/security concern because users may disclose more information than intended.

External Transmission

Medium
Category
Data Exfiltration
Content
## `/axolotl-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": "axolotl love" }'
Confidence
88% confidence
Finding
This endpoint sends relationship status metadata to an external service, which can expose behavioral or sensitive preference information if users do not realize it is remote and persistent. The action is core to the product, so the issue is not the existence of the call but the lack of explicit warning and context around the consequences of sending it.

Static analysis

No suspicious patterns detected.