amazon
Warn
Audited by Socket on Sep 23, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
Purpose and capabilities are mostly aligned, and the browser tooling appears to come from an official, verifiable source. The main risk is autonomy abuse: the skill empowers the agent to make real purchases and returns with limited user confirmation, including silent completion of returns and no confirmation for reorders.
Confidence: 92%Severity: 76%
Audit Metadata