open-notebook

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt instructs inserting secrets directly (e.g., exporting OPEN_NOTEBOOK_ENCRYPTION_KEY and POSTing {"api_key":"sk-..."}) which requires the LLM to accept and emit API keys/encryption keys verbatim, creating an exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.85). Outsider free text can be ingested via the runtime /api/sources URL/text ingestion path (e.g., user-supplied arbitrary URLs or raw text), which is then processed into searchable context and fed into the LLM during /api/chat/execute when include_sources/include_notes are enabled.

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

• Potentially malicious external URL detected (high risk: 0.90). The Quick Start instructs curling and using https://raw.githubusercontent.com/lfnovo/open-notebook/main/docker-compose.yml (followed by docker-compose up -d), which fetches remote deployment configuration that causes remote container images to be pulled and executed, satisfying the criteria for a runtime external dependency that executes remote code.