notebook-lm-research
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE] (SAFE): The skill consists entirely of documentation (SKILL.md) and does not contain any executable scripts, binaries, or package manifest files.
- [SAFE] (SAFE): No malicious patterns, prompt injections, or data exfiltration attempts were found within the instructional text.
- [Indirect Prompt Injection] (LOW): The skill is designed to analyze external documents, creating a theoretical surface for indirect prompt injection. 1. Ingestion points: Document Ingestion section (PDF, Google Docs, Web pages). 2. Boundary markers: Absent from the instructions. 3. Capability inventory: Limited to research synthesis and querying; no shell access, file-writing, or external network-send scripts detected. 4. Sanitization: No explicit sanitization or validation of source content is described.
Audit Metadata