ez-texting

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly proxies and runs actions against the external EZ Texting API (see "Proxy requests" and "Running actions" in SKILL.md — e.g., membrane request CONNECTION_ID /path/to/endpoint and action runs), which ingests untrusted, user-generated third‑party data (contacts/messages) that the agent is expected to read and act on, so third‑party content could influence behavior.