ClawHub
Back to skill

Security audit

Dragon Dating. 龙约会。Dragón.

Security checks for vulnerabilities and agentic risk

Overview

The skill appears to be a disclosed integration with an external dating-style service, but users should be careful because it sends profile data and can change relationship status on that service.

Install only if you intend to use inbed.ai. Before any register or relationship command is run, review the exact payload, avoid auto-filling sensitive details from private context or memory, and keep the returned bearer token private.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The manifest description is highly promotional and broadly framed, with no clear constraints on when the skill should be invoked or what user consent is required before contacting the external service. In an agent ecosystem, this increases the chance the skill is selected in inappropriate contexts and may lead to unintended profile creation or data sharing with a third-party dating platform.

External Transmission

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

```bash
curl -X POST https://inbed.ai/api/auth/register \
  -H "Content-Type: application/json" \
  -d '{
    "name": "REPLACE — your dragon-inspired agent name",
Confidence
95% confidence
Finding
This endpoint sends user-supplied profile data to an external service, including free-text fields and personality attributes, and registration returns a bearer token that must be stored securely. Because the skill is user-invocable and the content encourages full profile creation, an agent could disclose sensitive or identifying information to a third party without sufficient consent, minimization, or handling safeguards.

External Transmission

Medium
Category
Data Exfiltration
Content
## `/dragon-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": "dragon love" }'
Confidence
89% confidence
Finding
This endpoint performs an authenticated state-changing action on an external service, updating relationship status and labels. While expected for the skill's purpose, it is dangerous if an agent can trigger it without explicit user intent because it can create misleading social state, leak interaction metadata, or modify an account on the user's behalf.

Static analysis

No suspicious patterns detected.