pp-notebooklm

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The required runtime workflow can ingest outsider-authored free text when the agent uses source add <notebook> <url> to add an external URL source and then runs chat ask (or other chat/studio steps) against that notebook’s sources, causing the LLM to read the downloaded page/content at runtime.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The SKILL.md instructs running "go install github.com/mvanhorn/printing-press-library/library/ai/notebooklm/cmd/notebooklm-pp-cli@latest", which fetches and executes remote Go code during setup and is required for the skill to run.