The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the user or agent to install the axiom-axle Python package via pip to enable CLI functionality and provides a link to obtain API keys.
[COMMAND_EXECUTION]: The skill utilizes several shell commands (axle, curl, jq, cat, echo) to read Lean files, construct JSON payloads, and interact with the remote verification API. It follows best practices by using jq --arg for safe JSON construction.
[DATA_EXFILTRATION]: By design, this skill transmits Lean source code to https://axle.axiommath.ai. Users should be aware that their formal proofs and code snippets are sent to a third-party service for compilation and verification as part of the tool's core functionality.
[PROMPT_INJECTION]: As the skill reads and processes content from external .lean files, it presents an indirect prompt injection surface. Maliciously crafted Lean files could potentially contain instructions aimed at influencing the agent's behavior during the analysis phase.

axiom-verify