Open Notebook Skill

PassAudited by ClawScan on May 1, 2026.

Overview

The skill is a coherent local notebook integration, but users should notice that it relies on an external Docker-based service, stores notebook content across sessions, and references helper scripts that are not included.

Before installing, make sure you trust the open-notebook project and any Docker Compose file you run. Do not run missing helper scripts unless you obtain and review them separately. Treat notebook entries as persistent memory: avoid storing secrets or sensitive personal information unless you are comfortable with it being reused in later agent work.

Findings (3)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

Low

#ASI04: Agentic Supply Chain Vulnerabilities

What this means

A user might look for or run scripts that were not included in the reviewed artifacts.

Why it was flagged

The README describes helper scripts as skill files, but the provided manifest contains only README.md and SKILL.md. This is an incomplete-packaging/provenance note rather than evidence of malicious behavior.

Skill content

- `open-notebook-automation.ps1` - Core functions
- `on-query-handbook.ps1` - Query examples
- `create-notebooks.ps1` - Create thematic notebooks

Recommendation

Use only the included instructions unless you separately obtain and review any missing scripts from a trusted source.

Low

#ASI05: Unexpected Code Execution

What this means

Installing the surrounding open-notebook service may run local containers and change the local development environment.

Why it was flagged

The setup requires the user to start open-notebook with Docker Compose. This is expected for the stated local-service integration, but it does start background containers.

Skill content

docker compose -f docker-compose-host-ollama.yml up -d

Recommendation

Run Docker Compose only from a trusted open-notebook checkout and review the compose file before starting it.

Low

#ASI06: Memory and Context Poisoning

What this means

Information saved to notebooks may be reused in future agent sessions and could influence later answers.

Why it was flagged

The skill intentionally stores content for later retrieval. This persistent memory is central to the purpose and disclosed, but it can retain sensitive or inaccurate content.

Skill content

Enables saving and querying knowledge across sessions (second brain for agents)

Recommendation

Avoid saving secrets or untrusted instructions unless intended, and periodically review or clean notebook contents.