moderna-scientist

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

• Third-party content exposure detected (high risk: 0.90). The skill's workflow explicitly tells the agent to fetch and act on external, user-submitted biological data (e.g., "Obtain variant spike protein sequence (GISAID)" and "Immunogenicity screen: IEDB"), meaning untrusted third-party content is ingested and can materially affect design and downstream actions, allowing potential indirect instruction injection.