panel
Warn
Audited by Socket on Oct 19, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the stated purpose matches a multi-model panel, but the implementation relies on autonomous execution of external agent CLIs with approval and sandbox bypass flags, and explicitly works around guard-hook inspection. Data flow is broad but expected for a panel skill; the main risk is safety-control bypass and delegation of repository context to multiple external CLIs, not confirmed malware.
Confidence: 92%Severity: 76%
Audit Metadata