The Agent Skills Directory

[NO_CODE]: The skill consists exclusively of Markdown documentation and YAML configuration across two files (SKILL.md and invest.md). It does not include any Python, Node.js, or shell scripts.
[SAFE]: The skill provides investment analysis guidelines and risk management personas. It does not request access to sensitive file paths, hardcoded credentials, or perform unauthorized network operations.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest external macro data, central-bank policy context, and price trends. While this processing of untrusted data represents a potential attack surface, the skill lacks dangerous capabilities (such as file-write, command execution, or code evaluation) required for exploitation.

druckenmiller