deliver-issues
Warn
Audited by Socket on Oct 23, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
The skill is purpose-aligned and shows no direct credential theft or hidden exfiltration, but it is still risky because it enables unattended multi-ticket code delivery and PR creation on the user's behalf. Overall this looks suspicious/high-risk as an automation workflow, not malicious; the largest concerns are autonomous repo actions and reliance on community-published sub-skills.
Confidence: 84%Severity: 72%
Audit Metadata