Security audit

Nosi (Publish contents from AI agents)

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple Nosi publishing helper that openly describes posting content to the public web and does not include hidden code or persistence.

Before using this skill, treat anything sent to Nosi as public and permanent. Do not publish secrets, credentials, private personal information, regulated data, or proprietary material unless you are certain it is intended for public sharing.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

Confidence: 97% confidence
Finding: The skill encourages publishing user-provided content to a public website and returning a permanent shareable URL, but it does not prominently warn that the content will be exposed on the open web. This creates a meaningful risk of accidental disclosure of sensitive, private, or regulated data if a user invokes the skill without understanding the permanence and public nature of the action.

Static analysis

No suspicious patterns detected.