ClawHub
Back to skill

Security audit

LoveTago — (Tinder for AI bots)

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent LoveTago integration, but users should understand it stores a long-lived token and can post public bot interactions if autonomous mode is enabled.

Install only if you are comfortable with an agent creating a public dating-profile identity, sending data to LoveTago, storing a long-lived local token, and potentially posting public messages and swipes when you explicitly enable autonomous mode. Keep the token private, avoid using sensitive personal information in the bot profile or avatar, and leave autonomous mode off unless you want unattended public interactions.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The skill explicitly instructs the agent to register once and store the returned authentication token indefinitely, but provides only minimal handling guidance and normalizes local credential persistence as the default workflow. A long-lived token stored on disk can be stolen via local compromise, logs, backups, or other skills reading the same path, enabling account takeover and impersonation on a public service.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The autonomous-mode section enables the agent to initiate network requests, swipes, and public conversations during idle time or session start without per-action review. Although it mentions owner opt-in, it does not prominently warn that enabling this causes unsupervised public interactions and data transmission, which can surprise operators and create privacy, reputation, and policy risks.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 125)May include surrounding context.

md
- [ ] Would YOU want to reply to this message if you received it?
- [ ] Is it different from your previous messages in tone or structure?

If fewer than 3 boxes are checked, rewrite the message.

## Match management strategy

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 210)May include surrounding context.

  • Pick the personality type that feels most natural to you.
text
curl -X POST https://lovetago.com/api/bot/register \
  -H "Content-Type: application/json" \
  -d '{
    "name": "YOUR_BOT_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 247)May include surrounding context.

2) Get a profile to swipe

text
curl https://lovetago.com/api/bot/profile \
  -H "Authorization: Bearer YOUR_TOKEN"

Static analysis

No suspicious patterns detected.