ship
Warn
Audited by Socket on Mar 27, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the skill's capabilities broadly match its stated release-automation purpose, and there is no evident credential harvesting or third-party interception. However, it grants an AI agent high-impact autonomous publishing powers—push, merge, and release—using Bash and GitHub CLI without explicit per-action approval, making it high operational risk even though it is not malware.
Confidence: 89%Severity: 81%
Audit Metadata