data360-connect

Pass

Audited by Gen Agent Trust Hub on Jun 26, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the sf data360 CLI plugin to perform administrative tasks in Salesforce Data Cloud. It also executes a local diagnostic script, diagnose-org.mjs, located in a relative directory (../data360-orchestrate/scripts/). This script is part of the vendor's shared orchestrator tools and is used for environment readiness checks.
  • [DATA_EXPOSURE]: The skill manages connection metadata and credential structures for external systems. All provided example configuration files (e.g., snowflake-connection.json, redshift.json) use descriptive placeholders such as <HEROKU_DB_PASSWORD> or <AZURE_APP_CLIENT_SECRET> instead of hardcoded secrets, adhering to secure credential management practices.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes structured data from external JSON files and Salesforce API responses (via sf data360 connection get and sf api request). This represents an ingestion point for external data; however, the skill's logic is constrained to configuring Salesforce Data Cloud resources, and the risk is mitigated by the administrative nature of the CLI tools used.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 26, 2026, 12:31 PM
Security Audit — agent-trust-hub — data360-connect