The Agent Skills Directory

[SAFE]: No malicious instructions, prompt injections, or obfuscated payloads were identified in the skill content or scripts.
[COMMAND_EXECUTION]: The script scripts/compile-compact.py utilizes subprocess.run to execute the compact compiler. This is legitimate behavior for a tool-chain wrapper and does not involve shell injection vulnerabilities.
[DATA_EXFILTRATION]: The skill does not perform any network requests or access sensitive local data. All file operations in scripts/init-compact-project.py and scripts/generate-contract.py are limited to the creation and management of local project directories and boilerplate files.

midnight-compact