5dive-cli-extras
Warn
Audited by Socket on Sep 23, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
The skill is internally coherent for a 5dive runtime administration surface, not a credential-harvesting lure. Main risk comes from its legitimately powerful scope: root-level host actions, remote SSH fleet control, plugin/crew installation from repos or git URLs, and autonomous external actions like messaging, PRs, and publishing. Treat as high-privilege and medium-high security risk, but not malicious based on the provided content.
Confidence: 86%Severity: 71%
Audit Metadata