The Agent Skills Directory

[SAFE]: The skill instructions explicitly prioritize security by advising against hardcoding credentials and recommending the use of environment variables or existing configuration flows.
[SAFE]: Safety rules enforce paper trading by default and require the implementation of manual confirmation gates for any scripts capable of executing live trades.
[SAFE]: The AI is instructed to act in an advisory capacity only, ensuring that model outputs do not directly trigger order placement without deterministic code-level risk checks.
[SAFE]: No evidence of prompt injection, data exfiltration, or unauthorized command execution was found in the provided files.
[SAFE]: The packaged .skill file is a standard ZIP archive containing the same plain-text files provided for analysis, with no hidden payloads or obfuscated content.

alpaca-trading