plotting-agent
Warn
Audited by Socket on Apr 14, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The plotting purpose is coherent and the local fallback scripts are proportionate, but the optional PaperBanana integration materially increases risk: it delegates execution to an unpinned external codebase and may forward a Gemini API key and paper content through third-party code with unclear provenance. No direct malicious behavior is shown, but the install/execution trust and credential-forwarding model are inconsistent with a low-risk plotting skill.
Confidence: 87%Severity: 82%
Audit Metadata