full-send
Warn
Audited by Socket on Nov 18, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
The skill’s workflow is coherent with its stated purpose and does not show credential exfiltration or malicious execution. However, it explicitly authorizes consequential GitHub actions—including pushing and merging—while the user is not watching; this creates significant autonomy risk despite the stated gates. Treat as high risk for unattended repository actions, not confirmed malware.
Confidence: 96%Severity: 72%
Audit Metadata