byted-contextsearch-operator

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

• Third-party content exposure detected (medium risk: 0.30). In the data-plane runtime workflow (scripts/context_search.py → search()/chat()), the agent ingests outsider-authored free text from the user-provided --text/--message and sends it to Volcano’s /v2/search and /v1/chat/completions endpoints.