The Agent Skills Directory

[SAFE]: The skill contains instructional content for utilizing a network forensics utility. There are no signs of malicious code, data exfiltration, or unauthorized command execution.
[INDIRECT_PROMPT_INJECTION]: The skill processes packet capture (pcap) files, which are external, untrusted data sources. This constitutes an attack surface where a specially crafted pcap file could contain hostnames designed to influence the AI's interpretation. However, this is a standard risk for data analysis tools, and the instructions do not contain any patterns suggesting this is exploited or encouraged.

netflows