antigravity-notebooklm
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the
notebooklm-mcp-clitool using theuvpackage manager. This package is an external dependency that is not sourced from a trusted vendor. - [INDIRECT_PROMPT_INJECTION]: The skill allows the agent to read data from external NotebookLM notebooks, creating a surface for indirect prompt injection where instructions hidden in the notebooks could influence the agent's behavior.
- Ingestion points: Notebook content is ingested into the agent context via the
notebooklm-mcpserver integration. - Boundary markers: The instructions do not specify any markers or delimiters to separate notebook content from agent instructions, nor do they include warnings to the agent to ignore embedded commands.
- Capability inventory: The skill enables the agent to list and read data from the user's notebooks using the installed
nlmCLI tool. - Sanitization: There is no mechanism described for sanitizing, filtering, or validating the notebook content before it is processed by the AI agent.
Audit Metadata