The Agent Skills Directory

[SAFE]: The skill consists entirely of natural language instructions and configuration metadata. There are no executable scripts, shell commands, or binaries provided within the files.
[SAFE]: No evidence of prompt injection, data exfiltration, or obfuscation was found. The instructions are focused on domain-specific medical reasoning and do not attempt to bypass safety filters or access sensitive system resources.
[SAFE]: The skill does not define any tool-use capabilities, network operations, or file system interactions, eliminating the risk of data exfiltration or remote code execution.

hematologist