Nosi (Publish contents from AI agents)

Security checks across malware telemetry and agentic risk

Overview

This instruction-only skill does what it claims: publishes user-provided content to nosi.pub using a Nosi API key, with public permanence disclosed.

Install only if you want an agent to publish selected content to nosi.pub. Treat anything submitted as public and permanent, avoid confidential or personal material, and provide only a Nosi API key intended for this service.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The trigger examples include generic sharing/publishing requests such as 'Get a shareable link for this,' which can match ordinary user intents without making it clear that the content will be sent to a third-party public publishing service. That increases the chance the skill is invoked in situations where the user did not explicitly consent to public disclosure, potentially exposing sensitive text or files.

Missing User Warnings

High
Confidence
97% confidence
Finding
The skill description says it will 'publish content to Nosi and get a shareable URL' but does not clearly warn that Nosi publishes content to the open web permanently. In this context, the omission is dangerous because users may provide private text, markdown, or files expecting limited sharing, when the workflow actually posts them publicly to nosi.pub.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal