The Agent Skills Directory

[PROMPT_INJECTION]: The skill architecture presents a surface for indirect prompt injection (Category 8) by ingesting user-provided parameters to generate and execute code without explicit sanitization.
Ingestion points: User requests for model optimization and hyperparameter configurations as described in SKILL.md.
Boundary markers: Absent. The skill instructions do not define delimiters to separate user-provided data from system instructions.
Capability inventory: The skill is authorized to use the Bash(cmd:*) tool (defined in SKILL.md), which allows for broad command execution.
Sanitization: Absent. There are no specified validation or filtering steps for the input data before it is incorporated into generated code.
[COMMAND_EXECUTION]: The skill utilizes dynamic execution (Category 10) by generating and running Python scripts via the Bash tool to perform hyperparameter optimization tasks.

tuning-hyperparameters