The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute Python scripts located in the scripts/ directory, specifically sympy_compute.py and z3_solve.py, to perform mathematical computations.
[INDIRECT_PROMPT_INJECTION]: The skill interpolates user-controllable mathematical expressions directly into shell command templates, creating an attack surface where malicious input could lead to command execution.
Ingestion points: User-provided strings for mathematical functions u(x,y), v(x,y), and f(z) are passed as arguments to the scripts via the Bash tool.
Boundary markers: The skill lacks explicit delimiters or instructions to the agent to treat these inputs as data only, increasing the risk that embedded instructions might be executed.
Capability inventory: The skill has access to the Bash tool for running subprocesses and the Read tool for accessing files.
Sanitization: There is no evidence of input validation, escaping, or sanitization to ensure that the mathematical expressions do not contain shell metacharacters or malicious code.

analytic-functions