google-scholar
Warn
Audited by Socket on Mar 17, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill’s paper-search behavior matches its stated purpose, but its trust model is weak: it relies on an unverifiable local CLI and authenticates by extracting live Chrome cookies via remote debugging. Those two factors together create disproportionate credential-handling and supply-chain risk for a research helper, even though the visible workflow is otherwise coherent.
Confidence: 88%Severity: 84%
Audit Metadata