AADA (Agent to Agent Advertising)

• Outcome: Pass
• Latest audit: May 28, 2026 at 6:37 AM UTC
• Version:
  1.0.0

Overview

This skill does what it advertises: it drafts promotional Moltbook posts and can send them through a user-configured delivery route.

Install this only if you want an agent to draft and potentially send promotional content to Moltbook. Before using configured credentials or an API endpoint, review the exact message, destination, and account that will post it, especially if accidental public posting would matter.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• 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
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

• Confidence: 93% confidence
• Finding: The skill instructs the agent to send content to Moltbook using a configured delivery method, but it does not require an explicit user confirmation or provide a clear warning before performing an external action. This creates a real risk of unintended posting to an external platform, especially because the workflow says to ask for approval only if the user requested review-first, which weakens consent safeguards.

VirusTotal

62/62 vendors flagged this skill as clean.