creative-director

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to WebFetch public DESIGN.md files from the Design Inspirations Catalog (e.g., https://getdesign.md/{company}/design-md) — see Phase 3 in SKILL.md and references/design-inspirations.md — and to absorb those external, public design documents as creative inspiration, meaning untrusted third‑party content is fetched, read, and used to drive decisions and next actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs using WebFetch at runtime to retrieve design specs from URLs like https://getdesign.md/{company}/design-md, and those fetched DESIGN.md files include "Agent Prompts" (AI-readable design instructions), meaning external content fetched at runtime can directly control agent prompts.