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, andanalyze_cxrinSKILL.mdaccept 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
requestslibrary 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