protocol-reverse-engineering

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

• Third-party content exposure detected (high risk: 0.90). The skill ingests arbitrary network traffic and HTTP objects from untrusted third-party sources (e.g., mitmproxy/tcpdump/tshark captures and exports such as "tshark -r capture.pcap -Y "http" -T json" and Scapy code that prints/parses Raw payloads), so the agent would read and interpret user-generated or public web content.