fhir-ig-translate

Pass

Audited by Gen Agent Trust Hub on Jul 31, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides structured instructions and a helper script (scripts/ig-translate.sh) to manage German translation supplements for FHIR Implementation Guides. All operations are local and centered on file organization and validation.
  • [COMMAND_EXECUTION]: The skill uses a bash script (scripts/ig-translate.sh) which invokes python3 to parse local JSON resource files (fsh-generated/resources/*.json) to extract resource types and IDs. This is a standard project management task and does not involve untrusted input or shell injection vectors.
  • [EXTERNAL_DOWNLOADS]: The skill references official HL7 and vendor-owned repositories (e.g., github.com/forschungsgruppe-digital-health/*, github.com/FHIR/multi-lang-test-ig) for documentation and reference purposes. No remote code execution or automated downloads were detected.
  • [PROMPT_INJECTION]: The skill includes 'Trigger Prompts' in references/triggers.md used for testing agent activation. These are clearly labeled as testing data and do not attempt to bypass safety filters or override system instructions.
  • [DATA_EXFILTRATION]: No network operations or sensitive file access patterns were identified. The script only reads FHIR-related JSON files and project configuration files within the working directory.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 31, 2026, 06:19 PM
Security Audit — agent-trust-hub — fhir-ig-translate