monte-carlo-troubleshoot-agent-traces

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

• Third-party content exposure detected (medium risk: 0.30). The required workflow ingests outsider-authored free text from user-supplied trace/conversation IDs or from Monte Carlo alert-scoped breaching samples by calling get_agent_conversation / get_agent_trace / run_troubleshooting_agent, which can include prompts, completions, and transcripts as readable conversation content.