picqer

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

• Third-party content exposure detected (high risk: 0.75). At runtime the agent calls Apideck’s Ecommerce unified API (and possibly the Proxy API) to fetch Picqer resource data; those responses are outsider-authored content from the Picqer service that the agent will ingest as readable text/JSON into the LLM context.