Back to skill

Security audit

Molt Speak

Security checks across malware telemetry and agentic risk

Overview

The inspected skill bundle is coherent and disclosed; it contains powerful operational/admin workflows, but they are purpose-aligned and generally gated by user intent or explicit confirmation.

Install only if you need these operational workflows. Configure least-privilege API tokens, review any org memory/git sharing before use, and require explicit confirmation before production deploys, moderation changes, emails, monitor deletes, or Slack/Sentry write actions.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • 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

VirusTotal

54/54 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.