The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a local Python script (scripts/generate_emergency_card.py) to process medical data and generate various card formats.
[DATA_EXFILTRATION]: The skill accesses sensitive personal health information (PHI) stored in local directories, including data/profile.json, data/allergies.json, data/medications/medications.json, and surgical/discharge records. This access is integral to the skill's stated purpose of generating a medical emergency card.
[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it processes data from multiple local health record files without explicit sanitization. * Ingestion points: Reads health data from data/profile.json, data/allergies.json, data/medications/medications.json, and various surgical and discharge record files. * Boundary markers: The instructions do not implement specific delimiters or 'ignore' instructions for data extracted from health records. * Capability inventory: The skill possesses the capability to execute shell commands (running the card generation script) and write files to the local system. * Sanitization: No input validation or sanitization routines are defined for the content of the medical records before processing.

emergency-card