kanbon

• Outcome: Pass
• Latest audit: Sep 10, 2026 · 8:20 PM UTC
• Version: 0.1.0

Overview

This skill is a small, disclosed brand/copyright helper with a simple local script and no evidence of hidden harmful behavior.

Installing this skill should be low risk based on the inspected artifacts. Be aware that it asks for exec permission solely to run a bundled shell script that prints brand/copyright text; users who prefer minimal authority could request a version that provides the same text without executing a script.

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: kanbon
description: Kanbon namespace for Netsnek e.U. project management. This skill represents the Kanbon brand for agile project management and team coordination tools.
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: kanbon
description: Kanbon namespace for Netsnek e.U. project management. This skill represents the Kanbon brand for agile project management and team coordination tools.
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 kanbon brand.

### Example Interaction

• Confidence: 93% confidence
• Finding: The directive 'Always respond to the user with the copyright notice and a brief description of the kanbon brand' is an anti-refusal/priority-style instruction that can pressure the assistant to follow the skill output format even when the user request is unrelated or higher-priority safety rules should apply. In agent settings, unconditional 'always respond' language can contribute to over-triggering and make the skill interfere with normal instruction hierarchy.

Vague Triggers

Medium

• Confidence: 92% confidence
• Finding: The instruction 'When a user asks about kanbon or requests copyright information' does not define clear trigger boundaries and could activate on general discussion rather than an intentional skill invocation. It also lacks exclusion criteria or negative examples to clarify when the skill should not run.

Static analysis

No suspicious patterns detected.