fhir-ig-analysis

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill handles downloads of FHIR Implementation Guides from remote Git repositories and package URLs to perform analysis.
  • [COMMAND_EXECUTION]: The script uses subprocess.run to call git for metadata extraction and repository cloning. The implementation follows secure practices by using argument lists.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes third-party project files (Implementation Guides). While these constitute untrusted data, the skill's read-only nature and focus on quantitative metrics mitigate the risk of indirect prompt injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 06:10 AM
Security Audit — agent-trust-hub — fhir-ig-analysis