notebooklm
Warn
Audited by Socket on May 4, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The core purpose is coherent—querying NotebookLM via browser automation—but the trust model is weaker than it should be: it stores persistent Google session state locally, depends on third-party 'undetected' browser automation, and documents a transitive install path through an unrelated skills repo. Data flows go to official Google endpoints rather than obvious exfiltration hosts, so this is not confirmed malware, but it is a medium-high risk skill due to supply-chain and credential/session-handling concerns.
Confidence: 85%Severity: 72%
Audit Metadata