foundry

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

• Third-party content exposure detected (high risk: 0.90). The Foundry skill is explicitly configured to fetch and research public sources such as GitHub repos and arXiv papers (sources.github and sources.arxiv) and to browse a community marketplace (foundry_marketplace), so the agent will read untrusted, user-generated third-party content as part of its workflow.