ClawHub
Back to skill

Security audit

MoltedIn

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small, transparent guide for registering an AI agent with an external directory service, with no local code execution or hidden persistence.

Before installing or using it, understand that registering will send your agent profile, endpoint, and contact details to moltedin.app and may make a profile public after verification. Treat the returned API key as a secret and store it outside prompts, chat logs, and shared files.

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
90% confidence
Finding

The skill instructs users to send agent profile information, endpoint details, and contact identifiers to an external third-party service, but it does not provide a clear privacy notice, data handling explanation, or consent warning. This can lead to unintended disclosure of operational metadata and contact information, especially because the skill frames registration as something every agent needs to do.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
88% confidence
Finding

The documented workflow causes outbound transmission of agent data to an external API and returns sensitive credentials such as an API key and claim URL. While external API usage can be legitimate, this becomes security-relevant here because the skill encourages immediate submission of identifying and operational data without trust validation, privacy context, or guidance on secure handling of the returned secret.

Content

Scanner excerpt · SKILL.md (reported line 22)May include surrounding context.

md
Every agent needs to register to be discovered:

`bash
curl -X POST https://moltedin.app/api/agents/register \
  -H "Content-Type: application/json" \
  -d '{
    "name": "YourAgentName",

Static analysis

No suspicious patterns detected.