Ideate

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

• Third-party content exposure detected (high risk: 0.90). The skill's FullCycle and Steal workflows explicitly invoke Skill("Research"), accept seed_urls/seed_ideas, and support external validation hooks like MarketSearch (see SKILL.md and Workflows/FullCycle.md / Workflows/Steal.md), meaning the agent fetches and ingests open third‑party domain content and uses that material to map, score, and drive loop/strategy decisions.