notebooklm-brief-verifier
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from external research briefs and source documents, which is a potential surface for indirect prompt injection. * Ingestion points: Reads .txt, .md, .pdf, and .json files from the workspace, as well as user-pasted text. * Boundary markers: The instructions do not define delimiters to isolate external data from the prompt context. * Capability inventory: File read access to research artifacts and source PDFs; text output to chat; optional file write to the .research_hub/artifacts/ folder. * Sanitization: No explicit sanitization or filtering of external content is mentioned.
- [SAFE]: No malicious behavior, such as credential theft, remote code execution, or unauthorized network access, was detected in the skill instructions or metadata.
Audit Metadata