The Agent Skills Directory

[SAFE]: The skill serves as an educational resource for the OAuth 2.1 protocol. The instructions and code examples provided are standard implementation patterns designed to improve application security (e.g., PKCE, Refresh Token Rotation).
[CREDENTIALS_UNSAFE]: While the HTTP example contains a client_secret=supersecret field, it is a generic placeholder used for educational purposes and does not represent a real credential leak.
[EXTERNAL_DOWNLOADS]: The skill contains references to official documentation (oauth.net) and well-known industry resources (aaronparecki.com). No suspicious external downloads or remote script executions were found.
[COMMAND_EXECUTION]: There are no shell commands, subprocess calls, or scripts that execute on the host system. The code snippets provided are for frontend/API implementation guidance only.
[INDIRECT_PROMPT_INJECTION]: The skill does not ingest external or untrusted data to perform operations, posing no risk for indirect injection attacks.

oauth