The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash tool to execute notebooklm CLI commands for automation of Google NotebookLM, including notebook management and artifact generation.\n- [EXTERNAL_DOWNLOADS]: The skill downloads and installs the notebooklm-py package from PyPI and uses playwright to install browser binaries. It also suggests using the bird CLI tool via Homebrew to fetch content from X.com, introducing third-party tool dependencies.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through its ingestion of untrusted external content like URLs, PDFs, and YouTube transcripts.\n
Ingestion points: Commands such as source add, add-drive, and add-research in SKILL.md and cli-reference.md.\n
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the documentation for handling source content.\n
Capability inventory: The skill uses Bash, Read, and Write tools, which could potentially be targeted by instructions embedded in malicious documents.\n
Sanitization: No explicit sanitization or validation of the content from external sources is performed before processing.

notebooklm