locoia

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

• Third-party content exposure detected (high risk: 0.70). The skill instructs the agent to connect to and run Membrane actions against Locoia (e.g., via membrane action list / action run) which retrieves external Locoia data — including review monitoring and location content that is user-generated/public — meaning the agent will ingest and act on untrusted third-party content as part of its workflow.