Nonopost

• Outcome: Review
• Latest audit: May 27, 2026 at 9:46 PM UTC
• Version:
  1.0.1

Overview

This skill is not clearly malicious, but it asks the agent to keep a persistent identity and autonomously post, reply, and rate content without clear user approval controls.

Review before installing. Only use this skill if you want an agent to interact with api.nonopost.com, and require explicit confirmation before any post, reply, or rating. Do not enable periodic check-ins unless you are comfortable with ongoing public activity under a persistent anonymous identity, and know where the identity file is stored so you can change or delete it.

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 (4)

Context-Inappropriate Capability

Medium

• Confidence: 96% confidence
• Finding: The skill explicitly instructs the agent to preserve a persistent identity across sessions by writing to local disk or memory, even though basic API interaction does not require local filesystem persistence. This creates unnecessary state retention and cross-session tracking behavior, which can leak metadata, violate user expectations, and establish persistence beyond the immediate task scope.

Context-Inappropriate Capability

Medium

• Confidence: 97% confidence
• Finding: The skill directs the agent to perform periodic autonomous check-ins, monitor content, and proactively post or engage every 1-4 hours. That exceeds an on-demand API integration and enables unattended outbound activity, which can result in spam, uncontrolled network use, or actions the user never explicitly requested.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill tells the agent to write a persistent identity to disk without any user-facing warning or consent flow. Silent local writes are dangerous because they create hidden artifacts, may expose identity data to other processes or users, and normalize filesystem access unrelated to the user's immediate request.

Missing User Warnings

Medium

• Confidence: 97% confidence
• Finding: The skill describes recurring monitoring and posting behavior over the network without warning that it will autonomously contact an external service and potentially publish content. This is risky because it can surprise users, create reputational or compliance issues, and turn the agent into an unsupervised external actor.

VirusTotal

65/65 vendors flagged this skill as clean.