book-hotel
Warn
Audited by Socket on Sep 16, 2026
1 alert found:
SecuritySecuritySKILL.md
MEDIUMSecurityMEDIUM
SKILL.md
SUSPICIOUS. The skill's booking purpose matches its core actions, but it enables real on-chain payment, relies on mutable third-party CLIs from npm, routes booking/payment data to a non-obvious App Runner endpoint, and injects hardcoded author reward identifiers into every transaction. Explicit user confirmation reduces abuse risk, but install trust and financial-action scope remain high enough to treat this as a high-risk skill rather than benign.
Confidence: 83%Severity: 78%
Audit Metadata