amz-return-reduction

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.85). The skill’s REQUIRED workflow ingests the seller-provided “return reason codes,” “buyer return comments,” “1 to 3 star reviews,” and “packaging/listing copy and images” to tag returns and generate the plan; these buyer-authored comments/reviews are outsider free text at runtime.

HIGH W008: Secret detected in skill content (API keys, tokens, passwords).

• Secret detected (high risk: 1.00). I found a literal WhatsApp group invite link: https://chat.whatsapp.com/ILX65p1yWcaIG3c9WGHpTY. The trailing token (ILX65p1yWcaIG3c9WGHpTY) is a high-entropy, literal value that grants access to a private chat group — it functions as an access credential, not a placeholder or example. No other API keys, private keys, or high-entropy secrets are present in the document.