sf-integration

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to ingest and act on untrusted third-party API specs and service descriptions (e.g., SKILL.md's "External Service registration from OpenAPI specs" and the External Services/WSDL guides such as references/external-services-guide.md and assets/soap/wsdl2apex-guide.md) so the agent will read external OpenAPI/WSDL endpoints and generated responses that can change code generation and runtime callout behavior.