impeccable-june

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow explicitly tells the agent to fetch and verify public Unsplash images and to use image-search / web-fetch / browser access to resolve real photo URLs (reference/brand.md "Imagery" section and SKILL.md), and the critique flow (reference/critique.md) instructs loading and inspecting live URLs—so the agent ingests untrusted, user-generated third‑party content that can materially influence its decisions and actions.