The Agent Skills Directory

[SAFE]: The skill performs standard development environment setup tasks, such as creating .editorconfig, .vscode/settings.json, and .vscode/extensions.json files using predefined templates.
[COMMAND_EXECUTION]: The skill uses Bash exclusively for project reconnaissance (e.g., checking for the existence of files like package.json or .editorconfig using 'find' and 'test') and does not execute arbitrary or dangerous commands.
[EXTERNAL_DOWNLOADS]: The skill recommends well-known VS Code extensions (e.g., Microsoft Python, Rust-analyzer, Biome) from the official VS Code Marketplace, which is standard practice for project configuration. No direct downloads of executable code from untrusted sources are performed.
[DATA_EXFILTRATION]: No network operations or access to sensitive local data (e.g., credentials, SSH keys, or environment variables) were detected. The skill only interacts with local project configuration files.
[PROMPT_INJECTION]: No patterns indicative of prompt injection, instruction overrides, or attempts to bypass safety filters were found in the skill's instructions or metadata.
[DATA_EXPOSURE]: The skill does not access or hardcode any sensitive credentials. It follows best practices by using placeholders or recommending configuration via standard editor settings files.

configure-editor