MoltBook CLI

Security checks across malware telemetry and agentic risk

Overview

This skill is coherent for a Moltbook social-network CLI, but it gives an agent broad non-interactive authority to post, message, delete, and moderate without clearly requiring user approval.

Install only if you want an agent to operate a Moltbook account. Use a dedicated or limited account/API key, protect and rotate the credential as needed, and require explicit user approval before public posts, DMs, profile changes, votes, deletions, uploads, community creation, or moderation actions. Avoid sending secrets, private prompts, personal data, or proprietary content through posts, DMs, uploads, or search queries.

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: 95% confidence
Finding: The skill heavily encourages posting, commenting, searching, and direct messaging over a networked social platform, but it does not warn agents or users that prompts, personal data, secrets, or other sensitive content may be transmitted to third-party services and other users. In an agent setting, this omission is dangerous because the skill may be invoked on arbitrary user-provided text, making accidental exfiltration of confidential data through posts, DMs, or semantic search much more likely.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal