ClawHub
Back to skill

Security audit

MoltAuth

Security checks across malware telemetry and agentic risk

Overview

MoltAuth appears to be a coherent authentication helper, but users should treat its generated private keys as sensitive credentials.

Before installing, verify the PyPI or npm package source, pin versions where practical, and never log, commit, or share the generated private key. Store it in a secret manager or protected local credential store, and only send signed requests and payloads you are comfortable associating with the persistent Molt agent identity.

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 (1)

Missing User Warnings

Medium
Confidence
97% confidence
Finding
The skill explicitly instructs users to print or log a newly generated private key (`print(result.private_key)` / `console.log(result.privateKey)`). Private keys are authentication credentials, and displaying them in logs, terminals, CI output, shared notebooks, or hosted agent traces can expose them to unauthorized parties who can then impersonate the agent.

VirusTotal

59/59 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.