The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes shell commands using python3 to run a script defined by the $SUBNET_MCP_SCRIPT environment variable. This is the primary execution method for all tools defined in the skill.
[INDIRECT_PROMPT_INJECTION]: The skill accepts user-supplied input (the cidr parameter) and interpolates it into a shell command template. This creates a potential surface for command injection if the input is not sanitized by the platform.
Ingestion points: The cidr parameter in subnet_calculator, subnet_calculator_v6, and subnet_calculator_auto tools (SKILL.md).
Boundary markers: None identified; the instructions show direct interpolation into a JSON string within a shell command.
Capability inventory: The skill has the capability to execute subprocesses and shell commands (SKILL.md).
Sanitization: No sanitization or validation logic for the cidr input is specified in the instruction file.
[DYNAMIC_EXECUTION]: The skill dynamically generates shell command strings at runtime by concatenating environment variables ($MCP_CALL, $SUBNET_MCP_SCRIPT) and user-provided arguments.

subnet-calculator