sf-b2c-sfra

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

• Third-party content exposure detected (high risk: 0.85). The required workflow includes “Fetch live docs” via WebFetch/Web-search (e.g., GitHub pages and developer.salesforce.com search results), which are public outsider-authored web content that can be ingested as readable text into the agent’s 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 fetching live docs at runtime—e.g., the SFRA GitHub repository (github.com/SalesforceCommerceCloud/storefront-reference-architecture) and developer.salesforce.com search results—which would be retrieved during execution and used to control the agent's prompts/instructions.