bankr
Warn
Audited by Socket on May 14, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill is internally consistent and uses official Bankr package/docs/API surfaces, so it is not confirmed malware. However, its legitimate scope is still high risk: it grants an AI agent broad financial authority, routes keys and prompts through Bankr services, combines web browsing with transactional powers, and supports arbitrary signing/submission. The main concern is dangerous capability and autonomy exposure, not deceptive installation or mismatched data flow.
Confidence: 90%Severity: 86%
Audit Metadata