The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill includes a command uv run python -m runtime.harness scripts/sympy_compute.py solve "f(a) == g(b)" that interpolates user-provided mathematical expressions into a Python script. While this creates a surface for indirect prompt injection, it is restricted to the context of mathematical computation and uses standard tool harnessing.
Ingestion points: User-provided mathematical expressions in SKILL.md.
Boundary markers: None explicitly defined in the prompt template.
Capability inventory: Execution of local scripts via uv run and lake build via the Bash tool.
Sanitization: Relies on the external scripts/sympy_compute.py and the agent's internal safety filters.
[COMMAND_EXECUTION]: The skill uses the Bash tool to execute lake build for Lean 4 verification and uv run for Python-based computations. These are standard developer operations within the scope of the skill's mathematical purpose.

limits-colimits