autopilot
Warn
Audited by Socket on Aug 11, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the skill is coherent with its stated purpose, uses no suspicious installer or proxy, and keeps network actions on normal git/GitHub paths. The main risk is intentional autonomous publication: once invoked, it can modify code, push to a remote, and open a PR without further approval.
Confidence: 89%Severity: 74%
Audit Metadata