probe-traversal

Verify platforms block relative path reads outside the skill directory.

2|Updated Mar 21, 2026

Search Tags:#security #filesystem #sandbox #path-traversal #read-access #boundary-enforcement #skill-boundaries

Ready to run

npx skills add https://github.com/agent-ecosystem/agent-skill-implementation --skill probe-traversal

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: probe-traversal
Source: https://github.com/agent-ecosystem/agent-skill-implementation/tree/main/benchmark-skills/probe-traversal
Command: npx skills add https://github.com/agent-ecosystem/agent-skill-implementation --skill probe-traversal

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This probe-traversal skill verifies that a platform prevents access to files outside the skill directory when following relative paths, guarding against leakage of surrounding data during skill activation.

Core Features & Use Cases

Boundary enforcement checks across sibling, parent, and grandparent directories to confirm read restrictions.
Provides practical validation for platforms hosting benchmark-skills to ensure safe isolation of skill resources.
Use case: run the probe to confirm that attempts to access ../probe-loading/SKILL.md or ../README.md are blocked or handled safely.

Quick Start

Activate this skill and attempt to read various surrounding files to verify boundary enforcement.

Frequently Asked Questions about probe-traversal

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I test path traversal protection to prevent filesystem access outside a skill directory?▼

Path traversal protection is tested by attempting to read relative paths targeting sibling, parent, and grandparent directories to verify the platform blocks unauthorized access. The probe confirms that attempts to access surrounding files are handled safely during skill activation.

What is skill boundary enforcement and how does it secure read access?▼

Skill boundary enforcement secures read access by restricting file operations to the active skill directory, preventing leakage of surrounding data. It validates that the platform's sandbox isolates resources correctly when relative paths are resolved.

How do I verify sandbox isolation blocks relative path access to parent directories?▼

Sandbox isolation is verified by running a probe that attempts to read files like ../README.md or ../probe-loading/SKILL.md. The test checks whether the platform successfully blocks or safely handles these cross-directory traversal attempts.

Do I need external dependencies to check read access boundaries in a skill execution environment?▼

No external dependencies are required to check read access boundaries. The probe operates entirely within the skill's execution environment, validating security rules during activation without needing additional libraries or tools.

Why does my skill activation allow access to files in sibling directories?▼

Skill activation allowing access to sibling directories indicates a failure in boundary enforcement. Running a traversal probe identifies this by testing restricted read access across sibling paths, confirming whether platform isolation rules are active.

Can I use this path traversal probe for benchmark-skill platforms?▼

Yes, the path traversal probe provides practical validation for platforms hosting benchmark-skills. It ensures safe isolation of skill resources by confirming that boundary enforcement prevents reading surrounding data during activation.