ecwid

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

• Third-party content exposure detected (high risk: 0.70). The skill instructs the agent to use Membrane actions to fetch Ecwid store data (e.g., list-products, get-order, list-customers) from third-party stores, which are user-generated/untrusted content that the agent is expected to read and act on per the SKILL.md workflow.