principal-investigator

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

• Third-party content exposure detected (high risk: 0.80). This skill's workflow (SKILL.md and references/research-coordination-integration.md) explicitly delegates literature review and "review recent papers" / "research and validate normalization methods" to the program-officer/researcher, meaning the agent is expected to fetch and interpret public third-party literature which could materially influence decisions.