hardening-cloud-posture

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s runtime workflow includes “Reading External Sources” where it fetches arbitrary public pages as Markdown via a user-provided curl URL (with the extracted full page text ingested at runtime), which is outsider-authored free text and can be used for indirect prompt injection.