data360-harmonize

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the official Salesforce CLI (sf) to manage Data Model Objects (DMOs), identity resolution, and data graphs. All commands target an org alias provided by the user and include standard error suppression (2>/dev/null), which is typical for clean CLI tool output handling.
  • [DYNAMIC_EXECUTION]: The skill executes a local diagnostic script (node ../data360-orchestrate/scripts/diagnose-org.mjs). This is an expected pattern within this vendor's multi-skill ecosystem where a shared orchestration skill provides common diagnostic utilities. The script path is local and static, posing no remote code execution risk.
  • [EXTERNAL_DOWNLOADS]: The skill references local configuration templates and documentation within the data360-orchestrate directory. No external network downloads or remote script executions were identified.
  • [DATA_EXPOSURE]: While the skill interacts with sensitive data platform configurations, it does so through authenticated CLI sessions controlled by the user. No evidence of hardcoded credentials, unauthorized file access, or data exfiltration was found.
  • [PROMPT_INJECTION]: The instructions focus purely on workflow guidance and technical rules. There are no attempts to override agent safety filters or bypass system constraints.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 12:29 AM
Security Audit — agent-trust-hub — data360-harmonize