knowledge-book
Pass
Audited by Gen Agent Trust Hub on Mar 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill manages the book project structure by reading from local directories and writing markdown files to the disk, including a blueprint file and individual chapters in a dedicated directory.
- [EXTERNAL_DOWNLOADS]: The skill integrates with Google's NotebookLM service, referencing a specific notebook identifier (ff785860-29ee-4420-a576-cf449e65704f) to retrieve reference material.
- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection (Category 8) because it processes untrusted data from local files and external notebooks.
- Ingestion points: Data enters the agent context via local folder paths and NotebookLM queries.
- Boundary markers: No specific delimiters or safety warnings are used to isolate the ingested data from the system instructions.
- Capability inventory: The agent performs file read and write operations within the project directory.
- Sanitization: No explicit sanitization or validation of the retrieved text is mentioned before it is used for content generation.
Audit Metadata