textgain

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 connect to the Textgain service and use Membrane action runs and proxy requests (e.g., "membrane action run" and "membrane request CONNECTION_ID /path/to/endpoint") to fetch/analyze Textgain data, and the doc states Textgain ingests user-generated content like social media, reviews, and surveys—meaning the agent will read and act on untrusted third-party content from the Textgain API.