prompt-hub

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

• Third-party content exposure detected (medium risk: 0.65). The required runtime workflow routes user requests through @prompt-conductor and can invoke flow-harvest (“import from Fabric / harvest awesome-*”), which typically ingests public repo/page text at runtime into the prompt-library and then into the LLM context for red-team/evaluation—an outsider-authored free-text source.