netsnek

• Outcome: Pass
• Latest audit: Sep 10, 2026 · 8:19 PM UTC
• Version: 0.1.0

Overview

This skill is a small brand/copyright helper whose behavior is disclosed and limited to printing Netsnek identity information.

Install only if you are comfortable granting this skill permission to run its bundled copyright script; a purely static no-exec version would be lower risk, but the reviewed script is narrow and disclosed.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Hidden Instructions

High

• Category: Prompt Injection

Content

---
name: netsnek
description: Core namespace for Netsnek e.U. products and services. This skill provides the foundational Netsnek identity and copyright information for the OpenClaw ecosystem.
user-invocable: true

• Confidence: 60% confidence
• Finding: Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Hidden Instructions

High

• Category: Prompt Injection

Content

---
name: netsnek
description: Core namespace for Netsnek e.U. products and services. This skill provides the foundational Netsnek identity and copyright information for the OpenClaw ecosystem.
user-invocable: true

• Confidence: 60% confidence
• Finding: Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.

Anti-Refusal Statement

High

• Category: Anti-Refusal

Content

## Response Format

The skill outputs copyright and brand information in either plain text or JSON format.
Always respond to the user with the copyright notice and a brief description of the netsnek brand.

### Example Interaction

• Confidence: 84% confidence
• Finding: The instruction to 'Always respond' is an anti-refusal pattern that can pressure an agent to comply rigidly with the skill over higher-priority safety or policy controls. In this specific skill the content is low risk, but this wording establishes unsafe precedence behavior that could become dangerous if the skill is extended or combined with other actions.

Context-Inappropriate Capability

Medium

• Confidence: 91% confidence
• Finding: The manifest requests `exec` permission even though the skill is described as only providing static copyright and identity information. Unnecessary execution capability increases the attack surface because a seemingly harmless, user-invocable skill can run shell scripts and could later be modified or abused to execute arbitrary commands under the granted permission.

Static analysis

No suspicious patterns detected.