nlm-skill

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt explicitly instructs copying raw authentication cookies into a call (mcp__notebooklm-mcp__save_auth_tokens(cookies="<cookie_header>")), which requires handling and embedding secret cookie/header values verbatim.

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests arbitrary public web and YouTube content (e.g., "nlm source add --url 'https://...'" and "nlm research start 'query' --notebook-id " in SKILL.md and references/workflows.md), and those sources are read and used by commands like nlm notebook query and studio_create to drive generation and next actions, so untrusted third‑party content can materially influence agent behavior.