iblai-api-search

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

• Third-party content exposure detected (high risk: 0.70). The required workflow performs runtime HTTP GETs to outsider-controlled API endpoints (e.g., public platform content/agent catalog and RAG recommendations) and ingests the returned free-text fields like name/description into the agent’s context, which can include untrusted text from other authors.