deep-research
Warn
Audited by Socket on Oct 4, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The research workflow is broadly aligned with the stated purpose, but it processes untrusted web content while retaining write/execute capabilities and depends on a third-party local diagram skill with weak provenance. This is not confirmed malware, but the combination creates medium-high security risk and exceeds a purely documentation-style research footprint.
Confidence: 86%Severity: 74%
Audit Metadata