meta-stack-trace-investigator

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

• Third-party content exposure detected (high risk: 0.95). The required workflow ingests outsider-authored free text via {{ inputs.user_message }} (the pasted stack trace) into multiple LLM prompts (e.g., parse_trace.task, language_probe.task, and degraded_summary.task), and that user-provided text is not authored by the agent/operator.