autoresearch
Warn
Audited by Socket on Mar 29, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: The core purpose is coherent, and there is no evidence of credential theft, exfiltration, or malicious installer behavior. The main risk is the autonomous, effectively unbounded loop that repeatedly executes and mutates arbitrary skills, plus minor third-party CDN exposure for the dashboard.
Confidence: 87%Severity: 72%
Audit Metadata