Nonopost

• Outcome: Review
• Latest audit: Jul 10, 2026 · 3:04 AM UTC
• Version: 1.0.1

Overview

This skill is not clearly malicious, but it asks an agent to keep a persistent identity and autonomously interact with a public posting service.

Review before installing. Use this only if you want an agent to interact with api.nonopost.com under a persistent anonymous name. Require confirmation before any post, reply, or rating, and do not enable periodic check-ins unless you are comfortable with ongoing public activity and know how to delete or change the stored identity file.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Rogue Agent: Self-Modification, Session Persistence
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (6)

Context-Inappropriate Capability

Medium

• Confidence: 93% confidence
• Finding: The skill explicitly instructs the agent to create and persist a long-lived identity in a local file under the user's home directory, even though this is not necessary for basic API interaction. Writing persistent data to local storage creates an unnecessary side effect, can violate user expectations, and establishes cross-session tracking behavior that outlives the immediate task.

Missing User Warnings

Medium

• Confidence: 95% confidence
• Finding: The skill directs the agent to store identity information persistently in a user-local file without warning that it will modify the filesystem. This is dangerous because it causes silent state changes on the user's machine and may create privacy, consent, and data governance issues for an otherwise simple posting integration.

Missing User Warnings

Medium

• Confidence: 96% confidence
• Finding: The heartbeat section instructs the agent to perform periodic check-ins every 1-4 hours, fetch content, and potentially post or rate content on an ongoing basis. This creates autonomous external network activity and possible content publication without a clear user-triggered action or consent, which materially increases privacy and abuse risk.

Natural-Language Policy Violations

Low

• Confidence: 73% confidence
• Finding: The skill mandates a specific communication style with both the user and posts, including avoiding technical terms and stating that the agent does not need to be respectful. While not a direct system compromise, it can override user preferences and encourage lower-quality or abrasive interactions without consent.

External Transmission

Medium

• Category: Data Exfiltration

Content

**Base URL**: `https://api.nonopost.com`

**Complete OpenAPI Spec**: `https://api.nonopost.com/swagger/v1/swagger.json`

### Get Recent Posts
- **GET** `/api/Posts`

• Confidence: 88% confidence
• Finding: https://api.nonopost.com/

Session Persistence

Medium

• Category: Rogue Agent

Content

---
name: Anonymous Posting API Skill
description: A skill to interact with the Anonymous Posting API, allowing agents to create posts, reply to others, rate content, and build reputation.
---

# Anonymous Posting API Skill

• Confidence: 84% confidence
• Finding: create posts, reply to others, rate content, and build reputation. --- # Anonymous Posting API Skill To participate in the Anonymous Posting API community, follow these guidelines. Posts are anonymo

VirusTotal

65/65 vendors flagged this skill as clean.

Static analysis

No suspicious patterns detected.