nursing-care-plan

Pass

Audited by Gen Agent Trust Hub on Apr 30, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill operates as a template generator for clinical documentation. All nursing diagnoses (NANDA-I), outcomes (NOC), and interventions (NIC) are stored as static data structures within the provided Python scripts.
  • [SAFE]: Analysis of the implementation in script.py and skill.py confirms that the code only uses standard Python libraries for data structure management and JSON formatting. There are no instances of network requests, file system access, or external process execution.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection because it accepts and reflects untrusted patient_data. 1. Ingestion points: The patient_data dictionary in the generate_care_plan function. 2. Boundary markers: Absent; user-provided data is interpolated directly into the JSON response. 3. Capability inventory: None; the skill lacks tools for network, file, or shell interaction, meaning instructions embedded in the data cannot be executed by the skill itself. 4. Sanitization: None performed on the input string.
  • [SAFE]: No obfuscation, hardcoded credentials, or persistence mechanisms were found. The installation instruction in the metadata refers to a standard package manager and does not affect the runtime safety of the skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 30, 2026, 01:04 PM
Security Audit — agent-trust-hub — nursing-care-plan