integrate-napkin-agent-skills
Warn
Audited by Socket on Aug 20, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The core Napkin integration behavior is coherent and mostly proportional, and the `napkin-ai` install path matches official npm distribution. The main concern is the optional Pi package installation: Pi packages execute arbitrary code with full user permissions, and the skill references a package name whose provenance appears inconsistent with current npm evidence, making install trust unclear. No clear credential theft or covert exfiltration is present, but the third-party package install plus optional autonomous distillation makes this a medium-high security risk skill rather than benign.
Confidence: 84%Severity: 74%
Audit Metadata