amz-sourcing-diversification

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

• Third-party content exposure detected (medium risk: 0.65). The skill’s runtime workflow requires “Source quotes” by contacting suppliers or using industry directories, which commonly involves ingesting outsider-authored free-form supplier/website text (e.g., quote emails, directory listings) into the agent’s LLM context for comparison and plan generation.

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

• Secret detected (high risk: 1.00). I found a high-entropy WhatsApp invite URL in the document: "https://chat.whatsapp.com/ILX65p1yWcaIG3c9WGHpTY". This is a literal tokenized link that grants access to a private group (i.e., provides access to a service). It is not a placeholder, setup password, environment variable name, or redaction marker — therefore it meets the definition of a secret here.