the-librarian

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflows (references/stock.md) explicitly clone arbitrary public git URLs into the local library and the consult/research workflows (references/consult.md and references/research.md) require reading and synthesizing those repo files, meaning untrusted, user-generated third-party content from public repos is ingested and can materially influence the agent's findings and actions.