news
Warn
Audited by Socket on Mar 29, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill’s research and static-site generation are aligned with its purpose, and it pushes only to official GitHub endpoints, but the publish step is high risk: it extracts a GitHub token, stores it in plaintext via `credential.helper store`, and performs autonomous public publishing. Main concern is credential exposure plus unattended real-world action, not malware or third-party exfiltration.
Confidence: 91%Severity: 84%
Audit Metadata