sf-b2c-controllers

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.85). The skill’s required workflow includes “Web-fetch official sources” from public GitHub pages (e.g., github.com/SalesforceCommerceCloud/storefront-reference-architecture) and “Web-search” for documentation, which can cause the agent to ingest outsider-authored free text from fetched web pages into the LLM context at runtime.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly instructs the agent at runtime to "web-fetch" the SFRA repository (github.com/SalesforceCommerceCloud/storefront-reference-architecture), making that external content a required runtime dependency that will directly influence the agent's prompts/code generation.