The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes system commands by calling python3 $MCP_CALL to run the gtrace mcp utility. This allows the agent to perform network-related lookups such as ASN ownership, Geolocation, and Reverse DNS resolution.
[PROMPT_INJECTION]: Indirect prompt injection attack surface identified.
Ingestion points: Data enters the agent context through the ip parameter in the asn_lookup, geo_lookup, and reverse_dns tools, typically sourced from external network logs, traceroute hops, or user input (SKILL.md).
Boundary markers: Absent; the instructions do not specify the use of delimiters or 'ignore instructions' warnings for the processed IP strings.
Capability inventory: The skill is capable of executing subprocesses through the gtrace binary using the $MCP_CALL environment variable (SKILL.md).
Sanitization: Absent; the skill does not explicitly define validation or sanitization steps for the IP address input before it is interpolated into the command parameters.

gtrace-ip-enrichment