llm-radiology-use

Pass

Audited by Gen Agent Trust Hub on Oct 5, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external clinical data such as radiology reports and patient histories by interpolating them directly into prompt templates.
  • Ingestion points: Untrusted data enters the agent context via the report_text variable in analyze_report, the current and prior variables in compare_reports, and the findings and history variables in get_differential within SKILL.md.
  • Boundary markers: No explicit delimiters (like triple backticks or XML tags) or "ignore embedded instructions" warnings are used when interpolating external text into the prompt strings.
  • Capability inventory: The skill possesses the capability to write data to external datastores via the send_results_to_healthlake function using the boto3 library and to transmit data to various medical APIs via requests.post.
  • Sanitization: There is no evidence of input validation, escaping, or filtering of the clinical text before it is sent to the LLM providers.
  • [EXTERNAL_DOWNLOADS]: The skill makes network requests to external API endpoints for medical reasoning and data storage.
  • Evidence: The query_medpalm and medical_insights functions communicate with Google's generative language and health APIs (googleapis.com). The extract_medical_entities function communicates with Microsoft's Azure AI Health service (cognitiveservices.azure.com). The configure_healthlake function uses the boto3 client to interact with Amazon Web Services.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 5, 2026, 05:08 PM