laohan-notebooklm
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes multiple shell commands to manage directories (mkdir), copy script files (cp), and invoke CLI tools including the NotebookLM CLI (nlm) and the pdftoppm utility for PDF-to-image conversion.
- [EXTERNAL_DOWNLOADS]: The skill depends on the installation of the notebooklm-mcp-cli Python package and the poppler system library to perform its core tasks.
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests untrusted script data from user-provided file paths and processes them using the NotebookLM service.
- Ingestion points: The skill takes a file path to a script (script.md) as its primary input.
- Boundary markers: No explicit delimiters or instructions are used to separate the script content from the agent's instructions.
- Capability inventory: The skill has the capability to write to the local filesystem and perform network communication through the nlm tool.
- Sanitization: The script content is passed directly to the external service without validation or filtering.
Audit Metadata