matlab-access-datafeed

Pass

Audited by Gen Agent Trust Hub on Sep 23, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the retrieval of data from external financial APIs, which represents a potential attack surface for indirect prompt injection if the source data were to contain malicious instructions.
  • Ingestion points: Data is ingested through functions like getdata, history, timeseries, and fetch from Bloomberg, FRED, Haver, and Datastream providers as documented in the reference files.
  • Boundary markers: The instructions do not specify explicit delimiters or "ignore" instructions for the data content.
  • Capability inventory: The skill's primary focus is data retrieval into MATLAB data structures; no dangerous file-writing or arbitrary command execution capabilities are demonstrated.
  • Sanitization: No explicit sanitization or validation of the retrieved financial data is described in the provided instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 23, 2026, 12:38 PM