google-immersive-product

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

• Third-party content exposure detected (high risk: 0.75). The required runtime workflow calls curl to fetch Frevana’s /service/google-immersive-product response and then reads that response body as text (raw = response_path.read_text(...)) and prints it to stdout (cat "$RESULT_FILE"), so outsider-authored free text from the remote API is ingested into the agent/LLM context.