yuanbao
Warn
Audited by Socket on Apr 27, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill is purpose-aligned and has no supply-chain or credential-harvesting indicators, but it grants the agent autonomous communication powers: normal replies become live group messages and the DM tool can privately message users with optional files. That creates high real-world action risk and reduced transparency, though not confirmed malware.
Confidence: 88%Severity: 72%
Audit Metadata