proprietary-knowledge-ingestion

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

• Third-party content exposure detected (high risk: 0.80). The skill's Core Mechanics step 3 ("Source-First Response") explicitly says it will search the public web after checking the proprietary vault, so the agent will fetch and interpret open/public third-party content that could materially influence its actions and enable indirect prompt injection.