The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the Bash tool and the uv Python manager to execute local utility scripts (z3_solve.py, sympy_compute.py) for mathematical verification and computation. This is the intended operational mode for the skill's problem-solving capabilities.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it accepts mathematical expressions as input and passes them to shell-based tools. * Ingestion points: Mathematical expressions passed as arguments to Z3 and Sympy scripts in SKILL.md. * Boundary markers: Not present; user input is interpolated directly into command strings. * Capability inventory: The skill has explicit permission to use the Bash tool to run commands. * Sanitization: The instruction set does not provide any logic for validating or escaping the input strings before execution.

operator-theory