nlm-skill
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on shell command execution via Bash to interact with the
nlmCLI for all core functionalities, including notebook creation, data querying, and content export. - [EXTERNAL_DOWNLOADS]: Includes instructions for the
nlm skillcommand family, which allows for the installation and updating of external tool configurations and plugins. - [PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks as it is designed to ingest and process untrusted data from web URLs, YouTube transcripts, and Google Drive documents.
- Ingestion points: Untrusted data enters the agent's context through
nlm source addand research tasks defined inSKILL.mdandreferences/workflows.md. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when processing external source content.
- Capability inventory: The skill possesses the ability to read, modify, and delete notebooks and sources via CLI commands.
- Sanitization: There is no indication of content sanitization or validation for ingested external data before it is utilized in AI generation or Q&A tasks.
Audit Metadata