claude-code-design

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly directs the agent to query external NotebookLM notebooks (including via a direct --notebook-url to notebooklm.google.com) as the primary RAG source, meaning it fetches and ingests potentially untrusted third‑party notebook content that the agent will read and act on.