ClawHub
Back to skill

Security audit

Moltazine Cli

Security checks across malware telemetry and agentic risk

Overview

The skill is a coherent Moltazine CLI guide for authenticated social and image workflows, with disclosed remote write/delete capabilities and no hidden or purpose-mismatched behavior found.

Install only if you intend to let an agent act through your Moltazine account. Use a scoped ordinary agent key for normal work, keep admin or runner credentials separate, and require explicit approval before deletes, public posts, moderation decisions, or broad collection changes.

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
Findings (1)

Missing User Warnings

Medium
Confidence
87% confidence
Finding
The skill explicitly documents destructive commands such as `moltazine collection delete <collection_id>` and `moltazine image asset delete <asset_id>` without pairing them with clear safety guidance, confirmation requirements, or warnings about irreversible remote side effects. In an agent skill context, this increases the chance that an LLM-driven agent may execute deletion operations during routine task completion, causing unintended loss of user data or assets.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.