ai-detection-pipeline

Pass

Audited by Gen Agent Trust Hub on Oct 5, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest external data (DICOM URLs and binary data) which represents a potential attack surface for indirect prompt injection if the source data is untrusted.\n
  • Ingestion points: Functions such as submit_study_aidoc, analyze_chest_xray, and analyze_cxr in SKILL.md accept external URLs as input.\n
  • Boundary markers: The instructions do not define specific delimiters or warnings to separate external data from agent instructions.\n
  • Capability inventory: The skill uses the requests library to perform network operations and can trigger automated alerts via email/SMS.\n
  • Sanitization: The provided code snippets demonstrate basic API interaction but do not include input validation or sanitization logic for the processed URLs.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 5, 2026, 05:08 PM