jbdb-api

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

• Third-party content exposure detected (high risk: 0.85). The skill calls JBDB’s LoopBack REST API at runtime and ingests the returned JSON fields (e.g., cNotes, cPlaceString, cEventNotes) into the agent’s LLM context via summarize(); these texts originate from the public JBDB website (outsider-authored biographical notes), not the operating user.