retrieving-datacloud

Pass

Audited by Gen Agent Trust Hub on May 14, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the sf data360 CLI plugin to interact with Salesforce Data Cloud, performing tasks such as SQL queries, table descriptions, and search index lifecycle management.
  • [COMMAND_EXECUTION]: It invokes a local diagnostic script (diagnose-org.mjs) from the orchestrating-datacloud sibling skill to verify if the target environment is ready for Data Cloud operations.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection attack surface because it processes untrusted data retrieved from external database query results; however, this is inherent to its primary purpose as a data retrieval tool.
  • Ingestion points: Data returned from sf data360 query sql and sf data360 query vector commands.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded content are present in the prompt templates.
  • Capability inventory: The skill utilizes shell command execution via the sf CLI and node runner.
  • Sanitization: No explicit sanitization or validation of the retrieved database records is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
May 14, 2026, 02:47 PM