ccpa-consumer-requests

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). This workflow explicitly requires disclosing consumers' specific personal and sensitive information (e.g., SSNs, account details, passwords) in responses, which forces the LLM to handle and output secret values verbatim.

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

• Third-party content exposure detected (high risk: 0.75). The required runtime workflow ingests the consumer’s CCPA request content (e.g., via web form/email/phone intake) as free-form text into the agent context; this is outsider-authored user-submitted text from a party other than the operating user.