generating-ui-bundle-custom-app

Pass

Audited by Gen Agent Trust Hub on Jul 29, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill's design involves processing project configuration and user inputs, which is a standard functional requirement for metadata generation.
  • Ingestion points: Data is sourced from local sfdx-project.json files, directory structures, and user-provided application labels.
  • Boundary markers: The metadata templates utilize {braces} as delimiters for variable substitution.
  • Capability inventory: The skill allows the agent to write XML files to the project directory and execute Salesforce CLI (sf) commands.
  • Sanitization: The workflow relies on standard agent behavior for property resolution and does not include additional sanitization logic for the resolved variables.
  • [COMMAND_EXECUTION]: The skill uses the official Salesforce CLI (sf) to query organizational data and validate deployments.
  • Evidence: Instructions include standard CLI commands like sf data query and sf project deploy validate. These operations are well-known and expected within the Salesforce development lifecycle.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 29, 2026, 10:02 PM