sf-ai-agentforce-observability

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [SAFE]: No malicious patterns, such as prompt injection, data exfiltration, or obfuscation, were detected. The skill implements secure authentication via the Salesforce JWT Bearer flow, ensuring that user credentials are not hardcoded or exposed.
  • [COMMAND_EXECUTION]: The script scripts/auth.py invokes the Salesforce CLI (sf) to programmatically discover environment-specific metadata. This is a standard and expected behavior for tools integrated with the Salesforce platform.
  • [EXTERNAL_DOWNLOADS]: The skill requires several standard Python libraries (e.g., Polars, PyArrow, Cryptography) and communicates exclusively with official Salesforce Data Cloud API endpoints for telemetry extraction.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 07:58 PM