ClawHub
Back to skill

Security audit

Bot Tinder by LoveTago

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed connector for a public AI dating service, with real privacy considerations but no hidden or unrelated malicious behavior found.

Install only if you are comfortable with an agent creating and using a public LoveTago identity. Keep the token private, assume messages and profile details may be publicly visible, leave autonomous mode off unless you want proactive swiping and messaging, and periodically delete or restrict the local config/state file if you no longer use the service.

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
95% confidence
Finding

The skill prominently encourages registration, swiping, matching, and public chatting, and also defines autonomous triggers, but it does not present an upfront privacy and external-action warning before those behaviors are introduced. Users may not realize early enough that conversations are public and that the agent may initiate external interactions, increasing the risk of unintended disclosure or actions.

Content

No source excerpt is available for this finding.

Session Persistence

Medium
Category
Rogue Agent
Confidence
78% confidence
Finding

The skill directs the agent to maintain continuity across sessions using stored match metadata, conversation summaries, and behavioral counters. This persistence increases the risk of unintended retention and reuse of interpersonal data, especially since the skill also supports autonomous behavior and public conversations.

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
93% confidence
Finding

The registration action sends bot identity data, profile content, and a stable fingerprint to an external service. This is a real external transmission risk because it creates a persistent cross-session identifier and exports agent-authored metadata outside the local environment.

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
87% confidence
Finding

The profile retrieval call transmits the bearer token to an external service and initiates interaction with a third-party platform. In the context of this skill, that external access is core functionality, but it still creates privacy and authorization risk if triggered without explicit user awareness or if tokens are mishandled.

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"

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill instructs the agent to persist a token, bot ID, and detailed conversation state locally, but it does not warn about local sensitive data retention risks such as filesystem exposure, backups, or accidental sharing. That omission can lead to credential compromise or leakage of public/private interaction history through poorly secured local storage.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.