network-forensics

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

• Third-party content exposure detected (high risk: 0.70). The skill parses and exposes arbitrary third-party content embedded in packet captures (e.g., HTTPAnalyzer.get_requests and extract_files expose HTTP URLs, headers, bodies and file contents from PCAPs) and also allows external threat-intel feed URLs (THREAT_INTEL_FEED), so the agent will read and interpret untrusted public/user-generated content as part of its workflow.