nlm
Warn
Audited by Socket on Oct 5, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill’s stated purpose matches its NotebookLM-focused capabilities, but its trust model is weak: it requires a locally built `nlm` binary from `~/nix`, not a verifiable official distribution path, and that binary is given Chrome-derived NotebookLM session cookies/tokens plus access to local files for upload. Because an unverifiable CLI receives credentials, the skill meets the mandatory high-risk floor even without clear evidence of malicious intent.
Confidence: 84%Severity: 82%
Audit Metadata