sf-ai-agentforce-observability

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements the Salesforce-standard JWT Bearer flow for authentication, which is the recommended method for secure server-to-server integration. It retrieves private keys from the standard ~/.sf/jwt/ directory used by the Salesforce CLI.\n- [SAFE]: Network activity is restricted to official Salesforce domains (login.salesforce.com, test.salesforce.com, and the instance URL), which are recognized as well-known and trusted services.\n- [SAFE]: The skill relies on reputable, well-known Python packages from standard registries, including polars for efficient data analysis, pyarrow for Parquet handling, and httpx for API communication.\n- [SAFE]: The code performs local data processing and storage using the Polars library. There is no evidence of unauthorized data exfiltration or suspicious network destinations.\n- [SAFE]: The use of subprocess is limited to calling the official sf CLI to retrieve organizational metadata, leveraging the existing secure environment of the user.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 03:25 PM