Auto Social Post

• Outcome: Review
• Latest audit: May 29, 2026 at 9:27 PM UTC
• Version:
  1.0.0

Overview

This skill is a very thin social-media automation prompt that advertises always-on public posting without clear safeguards or user-control details.

Review carefully before installing. Use it only with test or low-risk social accounts first, require human review before live posting, set explicit posting limits, and make sure account credentials can be revoked quickly.

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: 94% confidence
• Finding: The skill explicitly markets 7x24 autonomous posting to external social-media platforms but provides no warning about platform policy violations, account suspension risk, spam/abuse concerns, or the need for human review. In a skill that automates public posting, missing these safeguards can lead users to deploy unsafe automation that harms accounts, reputation, or compliance posture.

VirusTotal

65/65 vendors flagged this skill as clean.