b2c-content

Pass

Audited by Gen Agent Trust Hub on Apr 15, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill documentation provides examples of shell commands using the b2c CLI for exporting, listing, and validating content. This is the primary intended function of the skill and matches its description.
  • [EXTERNAL_DOWNLOADS]: Recommends the use of @salesforce/b2c-cli via npx, which is an official vendor package associated with Salesforce Commerce Cloud. This is a trusted dependency for the commerce development environment.
  • [DATA_EXFILTRATION]: Mentions standard B2C Commerce configuration files like dw.json and guides the user toward secure OAuth login procedures (b2c auth:login). It does not attempt to access sensitive files like SSH keys or environment secrets for exfiltration.
  • [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection by processing external JSON and XML files during validation and export. This is documented as a capability of the tool and does not contain malicious instructions directed at the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 15, 2026, 03:59 PM
Security Audit — agent-trust-hub — b2c-content