staq
Warn
Audited by Socket on Oct 19, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill is internally coherent for a STAQ savings integration and contains substantial defensive checks against wrong addresses/calldata, but it still authorizes an AI agent to perform or trigger autonomous financial actions and route signed messages plus trade metadata through a third-party STAQ API whose provenance is only weakly verifiable from primary sources. No install-time malware or hidden exfiltration is evident, yet the real-world transaction scope keeps overall risk high.
Confidence: 90%Severity: 74%
Audit Metadata