eurouter-integration

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

• Third-party content exposure detected (high risk: 0.80). The skill's documentation and required examples (see references/code-examples-node.md and references/code-examples-python.md) demonstrate sending external image URLs (e.g., https://upload.wikimedia.org/…) as vision inputs to the model, which means the agent is expected to ingest and interpret arbitrary public third-party content as part of its workflow and that content could materially influence subsequent actions.