notebooklm
Warn
Audited by Snyk on Jun 14, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). The skill’s runtime workflow can ingest outsider-authored free text when it adds public web sources (e.g.,
notebooklm source add "https://..."ornotebooklm source add-research ... --from web), which NotebookLM then fetches/indexes and uses as readable content in subsequentnotebooklm ask/generateLLM context (indirect prompt injection via web page text).
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The install snippet fetches a release tag via https://api.github.com/repos/teng-lin/notebooklm-py/releases/latest and then runs pip install from the GitHub repo (git+https://github.com/teng-lin/notebooklm-py@${LATEST_TAG}), which downloads and installs remote code as a required dependency during setup, so it can execute remote code on the host.
MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).
- Hidden Unicode characters detected (1 type(s) found)
Issues (3)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
W012
MEDIUMUnverifiable external dependency detected (runtime URL that controls agent).
W021
MEDIUMHidden or invisible Unicode characters detected (potential obfuscation or prompt injection).
Audit Metadata