The Agent Skills Directory

[SAFE] (SAFE): No malicious code, prompt injections, or obfuscated payloads were detected. The skill consists entirely of markdown-based documentation and code templates.\n- [EXTERNAL_DOWNLOADS] (SAFE): The skill references standard development dependencies such as cloudflared and concurrently. These are reputable tools recommended for local development and tunneling, not for malicious downloads.\n- [COMMAND_EXECUTION] (SAFE): Documented shell commands (e.g., brew install, cloudflared tunnel, npm install) are provided as manual instructions for developers to set up their own local environments and do not represent a threat of automated or unauthorized execution.\n- [DATA_EXFILTRATION] (SAFE): References to sensitive file paths like ~/.cloudflared/cert.pem are part of legitimate configuration guides for the user's environment. No patterns for unauthorized data access or exfiltration were identified.\n- [SAFE] (SAFE): The skill promotes security-first development, including advice on configuring Content Security Policy (CSP), validating tool inputs with schemas, and managing authentication on the server side.

chatgpt-app-sdk