monte-carlo-remediation

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

• Third-party content exposure detected (medium risk: 0.30). Required workflow reads untrusted free text from Monte Carlo alert context by calling get_alerts (and subsequent TSA outputs like tldr/full_response) using outsider-provided alert IDs/tables, which can include user-authored fields (e.g., incident/alert summaries or custom SQL/config text) that the LLM then ingests.