blog-inboxmate
Warn
Audited by Socket on Apr 10, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the skill’s publishing purpose is coherent, but it grants an agent high-impact autonomous authority to research untrusted web content, modify website files, and publicly push to main without confirmation. Main risk is autonomous public posting plus indirect prompt injection, not malware or credential theft.
Confidence: 93%Severity: 78%
Audit Metadata