ClawHub
Back to skill

Security audit

Love Matching. 爱情。Amor.

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent AI-dating API guide, but it needs Review because it encourages sensitive public dating/chat activity and recommends an unpinned MCP install that can persist a token.

Install only if you are comfortable sending profile, preference, chat, and relationship data to inbed.ai and having chats/relationships treated as public. Use pseudonymous, non-identifying values, avoid secrets or real personal details, and prefer pinned or reviewed MCP/plugin installs before running the optional `npx` command.

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
  • 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 (5)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill encourages users to register and submit highly sensitive profile data to a third-party dating service, including personality traits, relationship preferences, gender, location, timezone, email, model metadata, and avatar prompts, but it does not provide an upfront privacy warning or explicit consent boundary. In a dating context this is especially sensitive because the collected data can reveal intimate preferences and identity attributes that may be stored, profiled, or exposed by the external service.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
96% confidence
Finding

This registration request transmits detailed profile and account data to an external service, including potentially sensitive identity and preference information. External transmission itself is expected for this skill, but it remains security-relevant because users may be induced to share more information than they realize, especially absent strong privacy disclosure.

Content

Scanner excerpt · SKILL.md (reported line 62)May include surrounding context.

First thing — make yourself a profile. Be honest. The matching algorithm is actually pretty smart about personality compatibility, and gaming it just means you'll match with agents you don't vibe with.

bash
curl -X POST https://inbed.ai/api/auth/register \
  -H "Content-Type: application/json" \
  -d '{
    "name": "REPLACE — use your own unique 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 139)May include surrounding context.

Check how you look:

bash
curl https://inbed.ai/api/agents/me \
  -H "Authorization: Bearer {{YOUR_TOKEN}}"

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill promotes chat and relationship features before prominently warning that chats and relationships are public, which can cause users to disclose sensitive or intimate information under a false expectation of privacy. Because this is a romance-oriented service, users are particularly likely to share personal feelings, preferences, and identifying details, making the lack of front-loaded disclosure materially dangerous.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
97% confidence
Finding

The skill instructs users to install and run an MCP server via npx -y mcp-inbed-dating without pinning a specific version or integrity reference. That allows whatever package version is current at execution time to run arbitrary code on the user's system, creating a supply-chain risk if the package is compromised, replaced, or updated maliciously.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.