The Agent Skills Directory

[PROMPT_INJECTION]: Instructions focus strictly on framework integration and development workflows. No attempts to override agent behavior, bypass safety filters, or extract system prompts were detected.
[DATA_EXFILTRATION]: No unauthorized file system access or network exfiltration patterns were identified. The skill correctly instructs users to manage sensitive keys via environment settings rather than hardcoding.
[CREDENTIALS_UNSAFE]: Examples use explicit placeholder strings (e.g., 'development-only-secret-32-chars') and demonstrate proper secret management using external settings files.
[EXTERNAL_DOWNLOADS]: All external references and documentation links point to official framework repositories or well-known technology service domains (e.g., inertiajs.com, vitejs.dev, litestar-org github).
[REMOTE_CODE_EXECUTION]: No evidence of unsafe remote script execution (e.g., curl | bash) or dynamic code evaluation using untrusted inputs.
[COMMAND_EXECUTION]: CLI commands are restricted to standard development tasks such as asset building, type generation, and development server management.
[OBFUSCATION]: The content is clear and readable. No hidden characters, multi-layer encoding, or homoglyph substitutions were found.
[DYNAMIC_CONTEXT_INJECTION]: No use of shell-interpolated dynamic context (exclamation-backtick syntax) was found in the skill definitions.

litestar-inertia