the-things-network

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

• Third-party content exposure detected (high risk: 0.80). This skill's mandatory workflow (e.g., "membrane action run" and "membrane request CONNECTION_ID /path/to/endpoint" in SKILL.md) queries The Things Network API via Membrane and therefore fetches and ingests potentially untrusted, user/device-generated third-party content which the agent is expected to read and act on.