shopwaive

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs the agent to fetch and interact with Shopwaive data via Membrane (e.g., membrane action list, membrane action run, and membrane request CONNECTION_ID /path/to/endpoint), which will ingest third-party Shopwaive API/page/blog/product content (user-generated/untrusted) and use those responses to determine actions and inputs, enabling indirect prompt injection.