analyzing-dns-logs-for-exfiltration

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

• Third-party content exposure detected (high risk: 0.75). The required workflow ingests DNS log fields like query/src_ip from runtime-provided Zeek/Splunk/SIEM data (outsider-authored network/domain text from external hosts), which the agent’s Python code reads and processes into LLM-visible output strings (e.g., printed alerts containing attacker-controlled domain/subdomain text).