blueprint

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

• Third-party content exposure detected (high risk: 0.80). The skill runs research tasks that perform web research (e.g., Skill("blueprint-research") in Phase 2 and Task(majestic-engineer:research:web-research) in Phase 8.1) whose findings (research_result) are ingested and used by the architect prompt and subsequent planning/execution, which clearly ingests untrusted public web/user-generated content that can influence actions.