chatlayer

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

• Third-party content exposure detected (high risk: 0.70). The SKILL.md shows the agent uses the Membrane CLI to connect to Chatlayer and run actions like select-table-records, get-table-data, and list-customers which fetch user-generated conversation/table data from the Chatlayer account (third-party content) that the agent is expected to read and could influence subsequent actions.