The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data in the form of network traffic and packet capture files. This creates a vulnerability surface where maliciously crafted network data could attempt to influence the agent's logic or output.
Ingestion points: Operations like rdpcap("capture.pcap") and tshark -r capture.pcap in SKILL.md ingest external data into the analysis workflow.
Boundary markers: No specific delimiters or instructions to ignore embedded commands within the processed packets are provided.
Capability inventory: The skill utilizes powerful capabilities including network packet transmission (send()), file writing (tshark -w), and interactive shell commands (wireshark, tcpdump) in SKILL.md.
Sanitization: There is no evidence of sanitization or validation of the data extracted from the network packets before it is processed.
[COMMAND_EXECUTION]: The skill provides numerous command-line examples for standard network tools like tcpdump, wireshark, and mitmproxy which are used for the primary purpose of protocol reverse engineering.

protocol-reverse-engineering