data360-connect

Pass

Audited by Gen Agent Trust Hub on Aug 7, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the Salesforce CLI (sf) and a local Node.js utility script (diagnose-org.mjs) to manage Data Cloud connectors and verify environment readiness. These operations are restricted to the local environment and the target Salesforce org specified by the user.
  • [CREDENTIALS_UNSAFE]: Example configuration files for Heroku Postgres, Snowflake, Redshift, and SharePoint (e.g., examples/connections/snowflake-connection.json) use descriptive placeholders like <HEROKU_DB_PASSWORD>, <AZURE_APP_CLIENT_SECRET>, and <YOUR_PRIVATE_KEY_WITHOUT_BEGIN_END_HEADERS> instead of hardcoding actual secrets.
  • [DATA_EXFILTRATION]: Configuration for external connectors involves standard endpoints for well-known services (e.g., login.microsoftonline.com for Azure/SharePoint). No evidence of data exfiltration to unauthorized or suspicious third-party domains was found.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests source metadata such as object and field names from external systems via the sf CLI. This represents a standard functional attack surface for integration tools and is managed through structured CLI command outputs.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 7, 2026, 01:00 PM
Security Audit — agent-trust-hub — data360-connect