netflows
Warn
Audited by Snyk on Feb 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill directly ingests user-supplied pcap/pcapng files and parses DNS responses, hostnames, and queried domains from those captures (dns_mappings, dns_queries), i.e., arbitrary third-party/user-generated network content that the agent reads and interprets.
Audit Metadata