The Agent Skills Directory

[SAFE]: The skill contains comprehensive instructions for error handling that emphasize security best practices, such as explicitly forbidding the logging of secrets, tokens, and credentials.
[SAFE]: It provides guidance on isolating transport-level exceptions from domain logic, promoting robust and predictable failure handling.
[SAFE]: The instructions regarding server-driven presentation hints explicitly warn against executing arbitrary commands or rendering raw HTML from external inputs, mitigating risks associated with indirect prompt injection or unauthorized code execution.

error-modeling