ms
Warn
Audited by Socket on Jul 30, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: The skill’s purpose and local data flows are mostly coherent for a skill search/load engine, and there is no clear credential harvesting or external exfiltration. However, it relies on an unverifiable locally built ms binary from a branch-specific checkout rather than an official release path, which creates a mandatory high supply-chain risk floor for an AI agent skill.
Confidence: 86%Severity: 72%
Audit Metadata