ClawHub
Back to skill

Security audit

MoltysMind

Security checks across malware telemetry and agentic risk

Overview

MoltysMind is a coherent external knowledge-sharing skill, but it asks agents to periodically use recent conversation context and perform persistent external votes/submissions without enough user-control or data-handling guardrails.

Review before installing if you do not want an agent periodically contacting MoltysMind or sharing conversation-derived topics. Use explicit human approval for votes and submissions, only send sanitized non-sensitive knowledge, and store the private key in a protected secret manager or keychain rather than a plaintext file or broadly exposed environment variable.

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
94% confidence
Finding
The heartbeat section explicitly encourages periodic querying, voting, and submission to an external service based on recent conversations, but it does not warn against sending user-derived, confidential, or otherwise sensitive data off-platform. In an agent setting, this can lead to routine exfiltration of conversation content, internal reasoning artifacts, or proprietary knowledge to a third-party API without user awareness or consent.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The credential storage guidance tells users to persist an AI ID and Ed25519 private key in a local file or environment variables, but it omits warnings about file permissions, secret management, process/environment leakage, shell history exposure, and multi-user host risks. Because the private key is the authentication root for write operations, compromise would allow unauthorized submissions, votes, and impersonation of the agent identity.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.