The Agent Skills Directory

[SAFE]: The skill's implementation is transparent and adheres to the stated purpose of providing clinical assessment scoring. No malicious patterns such as credential harvesting, unauthorized command execution, or persistence mechanisms were detected.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input, such as patient vitals and symptoms, to generate recommendations. While this creates a potential surface for indirect prompt injection, the risk is negligible as the skill possesses no dangerous capabilities (e.g., network or file system access).
Ingestion points: The run_assessment entry point in script.py processes patient assessment parameters.
Boundary markers: No specific delimiters are used for the input data.
Capability inventory: The skill logic is entirely computational and does not invoke subprocesses, network calls, or file writes.
Sanitization: Inputs are processed directly through scoring logic without external sanitization.
[EXTERNAL_DOWNLOADS]: The skill documentation provides an installation command targeting the vendor's official repository (Open-Medica/open-medical-skills).

patient-assessment-tool