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's interactive workflow interpolates user-provided input (the selected store name) directly into a shell command (sf project retrieve start -m DigitalExperienceBundle:site/<selected-store-name> --json). This pattern creates a potential vulnerability surface for command injection if an attacker provides a maliciously crafted store name containing shell metacharacters (e.g., semicolons or pipes).
  • Ingestion points: User-supplied store name input in Step 3 and site selection in Step 5 of SKILL.md.
  • Boundary markers: No shell-level delimiters or escaping mechanisms are applied to the user input before it is placed into the command string.
  • Capability inventory: The skill has the capability to execute Salesforce CLI commands (sf) which interact with the local filesystem and the connected Salesforce organization.
  • Sanitization: The instructions ask the agent to "validate" the input format, but there is no technical enforcement or programmatic sanitization to ensure the input is safe for shell execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 26, 2026, 12:31 PM
Security Audit — agent-trust-hub — commerce-b2b-store-create