The Agent Skills Directory

[SAFE]: Comprehensive review of the skill files found no malicious patterns, prompt injections, or security vulnerabilities. The content is strictly informational and instructional for clinical risk estimation.
[NO_CODE]: The skill does not include any executable scripts, shell commands, or external dependencies. All logic is provided as mathematical formulas and coefficients within markdown files.
[PROMPT_INJECTION]: No instructions were found that attempt to bypass AI safety filters, override system behavior, or deceive the agent.
[DATA_EXFILTRATION]: There are no network operations, hardcoded credentials, or accesses to sensitive file paths. The skill operates entirely within the provided context.

cardiovascular-risk