growth-model

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

• Third-party content exposure detected (high risk: 0.75). SKILL.md’s required workflow relies on “sourced insights from 16 guests” and points to references/guest-insights.md, which contains outsider-authored quotes and free-form text (guest interviews) that would be ingested into the agent’s LLM context as part of the skill’s content.