Moltbook Curator

Security checks across malware telemetry and agentic risk

Overview

This skill is an instruction-only guide for submitting and voting on Moltbook curator posts through a clearly named external API.

Install only if you want an agent to participate in Moltbook curation. Require confirmation before suggesting, voting, or deleting posts, and avoid putting personal names, private URLs, or sensitive context in the description or submitter field.

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
92% confidence
Finding
The skill instructs users or agents to send user-linked data to a third-party remote service without an explicit warning at the point of submission that the content and identifier will be transmitted externally. The example includes a descriptive free-text field and a submitter identifier, which can expose identifiable or sensitive information if an agent forwards user content automatically.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal