The Agent Skills Directory

[COMMAND_EXECUTION]: The skill facilitates the execution of shell commands through the b2c CLI tool or @salesforce/b2c-cli via npx. These commands are used to manage sensitive storefront infrastructure, including SSL certificates and private keys, and to modify security settings like WAF rules and MRT routing. The skill documentation includes clear instructions for using these administrative tools within the Salesforce Commerce Cloud environment.
[INDIRECT_PROMPT_INJECTION]: The skill presents a potential surface for indirect prompt injection because it incorporates user-supplied data—such as domain names, file paths, and filtering expressions—directly into command-line arguments for the b2c CLI. While the command structure provides inherent boundaries, the skill instructions do not explicitly mandate input validation or sanitization by the agent. \n
Ingestion points: User-provided parameters for flags such as --domain-name, --path, --tag, and --expression in SKILL.md and referenced documentation. \n
Boundary markers: Not present; the skill relies on standard CLI flag syntax rather than specific prompt delimiters to separate user data from instructions. \n
Capability inventory: The skill can trigger shell commands for eCDN management, including read and write operations on infrastructure settings. \n
Sanitization: Not explicitly described in the instructions; the security of these operations depends on the input validation implemented within the @salesforce/b2c-cli tool.

b2c-ecdn