Experimental NotebookLM harness for listing notebooks, managing sources, asking questions, generating artifacts, and downloading outputs through an installed notebooklm CLI.
75%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./notebooklm/agent-harness/cli_anything/notebooklm/skills/SKILL.mdThe skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The agent workflow interacts with Google NotebookLM via a CLI harness to manage notebooks and sources, which can ingest external web pages or documents added as sources.
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.