The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes untrusted user input that influences the generation and execution of code, creating a potential vector for indirect prompt injection.\n
Ingestion points: User-provided mathematical theorems and conjectures used for verification and proof construction as described in SKILL.md.\n
Boundary markers: The instructions do not define delimiters or markers to isolate user-supplied data from the agent's logic.\n
Capability inventory: The skill utilizes jupyter_execute for code execution, along with latex_compile and update_latex for document modification.\n
Sanitization: There are no mechanisms specified for validating, escaping, or filtering user input before it is used to drive computational verification tasks.

theorem-proving