interactive-research
Warn
Audited by Socket on Jul 17, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill’s purpose is coherent and its external endpoints are mostly official, but it combines broad execution/write privileges with heavy ingestion of untrusted web content and multi-agent autonomy. That makes it a high-risk research skill due primarily to indirect prompt-injection and external data-sharing exposure, not confirmed malware.
Confidence: 88%Severity: 72%
Audit Metadata