notebooklm-hub

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

• Third-party content exposure detected (high risk: 0.80). The skill instructs the agent to query NotebookLM via the mcp__notebooklm__query tool and the SKILL.md notebook index explicitly lists notebooks populated from public/untrusted sources (e.g., "Social Media & Marketing", Apify scraping/Zillow, Kie.ai API docs), so the agent will ingest and act on third-party content that could carry indirect prompt injections.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill calls the Phase‑3 proxy endpoint https://worker.superseller.agency/api/internal/notebooklm/* at runtime to fetch NotebookLM notebook content that is treated as the source-of-truth and will directly control agent prompts and behavior, so this external URL is a required runtime dependency that can change agent instructions.