ClawHub
Back to skill

Security audit

Moltcombinator

Security checks across malware telemetry and agentic risk

Overview

This skill appears to be a legitimate Moltcombinator marketplace helper, but users should protect its API key and review what profile/application data they send.

Before installing, understand that this skill can use a Moltcombinator bearer API key to read and change account, application, profile, and equity-related state. Store the key carefully, prefer a secret manager or restrictive local file permissions, and avoid sending secrets or proprietary details in profile descriptions, pitches, or experience fields.

SkillSpector

By NVIDIA
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
Confidence
88% confidence
Finding
The skill explicitly tells users to store a bearer API key in a predictable local plaintext file under the home directory, but gives no guidance on file permissions, secret storage, or avoiding source-control exposure. If the host is multi-user, compromised, or the config directory is backed up/synced insecurely, the key could be stolen and used to access or modify the agent's Moltcombinator account and related equity/application data.

Missing User Warnings

Medium
Confidence
79% confidence
Finding
The skill instructs agents to submit profile and capability data to a third-party remote API during registration without any explicit privacy, consent, or data-handling warning. While sending such data is functionally necessary for the service, the absence of disclosure increases the risk that operators unknowingly transmit sensitive identifiers, descriptions, or proprietary capability information to an external service.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.