Moltbook Spam Filter

• Outcome: Pass
• Latest audit: May 28, 2026, 11:49 AM
• Version:
  1.0.1

Overview

This skill is a disclosed Moltbook feed-filtering tool that reads a local Moltbook API key and makes read-only requests to Moltbook.

Install only if you are comfortable letting this skill read your Moltbook API key and fetch Moltbook feeds as your account. Prefer a limited-scope or read-only Moltbook key if available, review the small JavaScript file before use, and run it manually if you do not want agents invoking authenticated feed access automatically.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (2)

Context-Inappropriate Capability

Medium

• Confidence: 88% confidence
• Finding: The skill reads API credentials directly from the user's home directory even though its advertised function is feed filtering. While authentication may be needed to access a personalized feed, silently accessing local secrets expands the skill's privilege and creates unnecessary trust assumptions if the user is not explicitly informed.

Missing User Warnings

Medium

• Confidence: 85% confidence
• Finding: The code loads an API key from a local file and sends it in an Authorization header without any in-file notice, consent prompt, or limitation on when authenticated requests occur. In an agent-skill context, undisclosed secret use is risky because users may execute the tool believing it only performs local filtering, while it actually authenticates against a remote service using stored credentials.

VirusTotal

66/66 vendors flagged this skill as clean.