The Agent Skills Directory

[COMMAND_EXECUTION]: The skill is designed to execute a local Python script scripts/setup_experiment.py located within the skill's directory. This is used to process experiment parameters and initialize configuration files.
[INDIRECT_PROMPT_INJECTION]: The skill possesses an ingestion surface for potentially untrusted data through its interactive setup mode.
Ingestion points: User-provided inputs for domain, experiment name, target file, and especially the evaluation command in SKILL.md.
Boundary markers: None are explicitly defined in the prompt instructions to delimit user-provided commands from the execution context.
Capability inventory: The skill executes shell-level commands via the python interpreter targeting scripts/setup_experiment.py.
Sanitization: The documentation does not specify sanitization or validation routines for the eval command provided by the user before it is passed to the execution script.

setup