sf-b2c-ocapi

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

• Third-party content exposure detected (high risk: 0.75). The skill’s runtime workflow includes WebFetch of Salesforce documentation pages (e.g., developer.salesforce.com/.../b2c-ocapi-overview.html), which is outsider-authored public web content that can be ingested as readable text into the agent’s LLM context.

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 to WebFetch the live documentation at developer.salesforce.com/docs/commerce/b2c-commerce/guide/b2c-ocapi-overview.html at runtime ("Fetch live documentation BEFORE writing any code"), so remote content will be fetched and can directly influence prompts/instructions and is treated as a required dependency.