skills/secondsky/sap-skills/sap-rpt1/Gen Agent Trust Hub

sap-rpt1

Pass

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The documentation references the official SAP-samples GitHub repository (github.com/SAP-samples/sap-rpt-1-oss) for installing the core model inference library. This is a well-known technology organization.
  • [DATA_EXFILTRATION]: The scripts check for the presence of a Hugging Face authentication token in standard local cache directories (~/.cache/huggingface/token) to provide user hints about model access. No credentials are hardcoded or transmitted externally.
  • [COMMAND_EXECUTION]: The skill provides scripts for local execution (fico_data_prep.py and rpt1_oss_predict.py) that require a Python 3.11 environment. These scripts perform structured data processing and model inference without requiring administrative privileges or performing unsafe shell operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 19, 2026, 02:25 PM
Security Audit — agent-trust-hub — sap-rpt1