autodev-loop

Warn

Audited by Socket on Mar 17, 2026

1 alert found:

Security
SecurityMEDIUM
SKILL.md

SUSPICIOUS. The skill’s capabilities broadly match its autonomous-dev purpose, but its security footprint is high: persistent cron-driven autonomy, code/write/exec/git-push authority, and extensive reliance on an unresolved `npx lev` CLI with unverified provenance. No clear credential theft or covert exfiltration is shown, so this is not confirmed malware, but it is a high-risk workflow skill.

Confidence: 87%Severity: 86%
Audit Metadata
Analyzed At
Mar 17, 2026, 09:28 PM
Package URL
pkg:socket/skills-sh/lev-os%2Fagents%2Fautodev-loop%2F@d34032e13a783324c652f235ce769a27a1036b13
Security Audit — socket — autodev-loop