nicereply

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md instructs the agent to connect to Nicereply via Membrane (e.g., "membrane connect --connectorKey nicereply" and "membrane action run ...") and to read/run actions that return Nicereply survey/feedback data (user-generated, third-party content) which the agent is expected to interpret and could materially influence subsequent actions.