draft-landing

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

• Third-party content exposure detected (high risk: 0.75). At runtime the workflow runs python3 -m draft_agent.uiux search against --domain landing and --domain product, which likely fetches public/community landing-page and product-reasoning text (outsider-authored) and feeds it into the agent’s LLM context for pattern validation.