The Agent Skills Directory

[PROMPT_INJECTION]: The skill incorporates user-supplied input from the $ARGUMENTS placeholder directly into the execution context of the simulation without sanitization.
Ingestion points: User input enters via the $ARGUMENTS variable defined in SKILL.md.
Boundary markers: The input is not wrapped in delimiters or accompanied by instructions to ignore embedded commands, which could allow a user to influence agent behavior or execution flow.
Capability inventory: The skill uses allowed-tools including Bash (for python, cd, and uv) and Read operations.
Sanitization: No input validation or escaping mechanisms are described to ensure the arguments are restricted to safe flags or scenario names.
[COMMAND_EXECUTION]: The skill executes shell commands via uv to navigate directories, synchronize dependencies, and run the Python simulation script (src/main.py).

sim