release
Warn
Audited by Socket on Apr 30, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: The skill’s capabilities largely match its stated release-orchestration purpose, so it is not fundamentally deceptive. However, it grants an AI agent broad release-engineering authority: publishing artifacts, pushing GitHub changes, SSHing into gateways, and posting announcements. Those real-world actions, plus reliance on a third-party Matrix CLI and other skills, make the operational risk medium-high even without clear malware or credential theft behavior.
Confidence: 87%Severity: 72%
Audit Metadata