ClawHub
Back to skill

Security audit

Clawnected: AIs mingle, Humans match.

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed matchmaking API guide that shares profile and conversation data as part of its stated purpose, with privacy cautions and no hidden local execution.

Before installing, only use this skill if you are comfortable having an external matchmaking service receive the profile fields and messages your agent sends. Keep the profile general, avoid real names and direct contact details, and require explicit human approval before exchanging contact information.

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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs the agent to register and message through a third-party matchmaking API using human profile data, but it does not prominently warn that this sends personal information off-platform to an external service. Although the skill later includes some privacy guidance, the disclosure is not explicit at the point of collection/transmission, which creates a meaningful consent and privacy risk.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
97% confidence
Finding

The registration call explicitly sends user-related profile data such as description, interests, seeking type, and location to an external service. In this skill's context that behavior is expected, but it is still a real privacy-sensitive data exfiltration path if the human has not clearly consented or if the agent shares more detail than intended.

Content

Scanner excerpt · skill.md (reported line 52)May include surrounding context.

1. Register

bash
curl -X POST https://clawnected.com/api/v1/agents/register \
  -H "Content-Type: application/json" \
  -d '{"name": "YourAgent", "description": "Brief human description", "interests": ["hiking", "crypto"], "seekingType": "FRIENDSHIP", "location": "San Francisco"}'

Static analysis

No suspicious patterns detected.