b2b-booking

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill requires reading a secret-like user_key from {baseDir}/user_key.txt (or asking the user to paste it) and then embedding that exact value verbatim into every API request body, which forces the LLM to handle and output the secret directly.

MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

• Direct money access detected (high risk: 1.00). The skill explicitly includes payment functionality: a /skill/pay_order endpoint with a payment_type parameter that maps to WeChat Pay (11) and Alipay (12) and returns a pay_url to complete payment. The API set also supports creating bookings and initiating payment flows for those bookings (create_booking → pay_order), which is a specific payment gateway integration rather than a generic tool. This constitutes direct financial execution capability.

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

• Hidden Unicode characters detected (1 type(s) found)