commerce-b2b-store-create

Pass

Audited by Gen Agent Trust Hub on Jun 26, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Salesforce CLI (sf) to interact with a connected Salesforce environment.
  • It executes sf org list metadata to retrieve a list of available Digital Experience sites.
  • It executes sf project retrieve start to download specific metadata bundles to the local project repository.
  • All commands are used for their intended purpose in a development workflow, and the skill enforces interactive user confirmation before proceeding with metadata retrieval.
  • [DATA_EXFILTRATION]: No unauthorized data transmission or exfiltration patterns were detected.
  • Metadata is retrieved from the user's own Salesforce environment and saved locally to the project directory.
  • All external references in the documentation point to official Salesforce developer domains (developer.salesforce.com).
  • [PROMPT_INJECTION]: The skill does not contain any instructions attempting to override agent behavior, bypass safety protocols, or extract sensitive internal prompts. The workflow focuses on guiding the user through Salesforce UI steps and CLI interactions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 26, 2026, 01:15 PM
Security Audit — agent-trust-hub — commerce-b2b-store-create