ai-scientist
Warn
Audited by Socket on Apr 8, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The core issue is install-trust mismatch: the skill presents itself as a wrapper for SakanaAI/AI-Scientist-v2 but directs installation of a separate PyPI package with no verified same-org relationship. The requested capabilities otherwise fit the stated research purpose, but forwarding API keys to an ambiguously sourced package materially raises risk.
Confidence: 90%Severity: 83%
Audit Metadata