performing-dns-tunneling-detection

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly ingests untrusted, third‑party DNS traffic from PCAP files and live captures (see scripts/agent.py use of rdpcap/sniff and SKILL.md examples reading "dns_traffic.pcap"), and the agent parses those query names and uses their contents to drive detection decisions, so external data could indirectly influence its actions.