customer-profile

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

• Third-party content exposure detected (low risk: 0.10). The skill’s required runtime workflow centers on using the user’s own answers plus first-party “memory/…” files, and any community/web “research” is framed as the agent actively seeking people/proof of pain rather than ingesting arbitrary outsider-authored text without selection, so it aligns with “low” rather than “medium.”