prava-agent-payments
Warn
Audited by Socket on May 9, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS: the skill is coherent for agent payments, and its main data flow goes to same-brand Prava infrastructure, but it grants an AI agent the ability to complete real purchases using returned payment credentials and includes external CLI/skill update trust paths. This is not confirmed malware, but it is high-risk due to autonomous financial action and sensitive credential handling.
Confidence: 83%Severity: 72%
Audit Metadata