flexport-data-handling
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill follows security best practices for handling sensitive logistics data.
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external API sources which represents a theoretical injection surface; however, it implements significant mitigating controls.
- Ingestion points: Shipment data is fetched from the official Flexport API via the
importShipmentsfunction inSKILL.md. - Boundary markers: Explicit boundary markers for LLM context are absent, though the logic focuses on structured data transformation.
- Capability inventory: The skill uses the
writeFiletool to save processed shipment data to the local filesystem inSKILL.md. - Sanitization: The skill implements field-level PII redaction for contacts and validates HS codes against restricted trade compliance lists (ITAR/EAR).
Audit Metadata