snek

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

Overview

This is a small Snek/Netsnek copyright helper; its script only prints brand and copyright text, with minor wording and encoding issues but no harmful behavior found.

Install this only if you want a Snek/Netsnek identity and copyright helper. Be aware it requests exec permission to run a bundled shell script and its trigger wording is broad, but the inspected script only prints fixed text or JSON and does not access local data or the network.

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
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• 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: snek
description: Snek namespace for Netsnek e.U. utility tools. This skill provides the Snek brand identity, a lightweight collection of helper functions and common utilities used across Netsnek products.
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: snek
description: Snek namespace for Netsnek e.U. utility tools. This skill provides the Snek brand identity, a lightweight collection of helper functions and common utilities used across Netsnek products.
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 snek brand.

### Example Interaction

• Confidence: 85% confidence
• Finding: The instruction 'Always respond to the user with the copyright notice and a brief description of the snek brand' is an anti-refusal style directive that attempts to force a fixed output regardless of user intent or higher-priority safety constraints. In isolation it is low risk, but in agent settings this pattern can weaken policy compliance and encourage the model to ignore context, making prompt-injection chaining easier.

Vague Triggers

Medium

• Confidence: 95% confidence
• Finding: The instruction to run the skill "when a user asks about snek or requests copyright information" is ambiguous and broad. "Requests copyright information" could overlap with many unrelated contexts, and the file does not provide narrower trigger phrases, scope limits, or exclusion examples to prevent unintended invocation.

Static analysis

No suspicious patterns detected.