ent

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

• Third-party content exposure detected (medium risk: 0.30). The runtime workflow loads and executes the project’s .ent.el/ent init file from the provided :dir and then reads the contents of the resulting *ent-log* buffer (via agent-skill-ent--result / agent-skill-ent-log), so outsider-authored free text can enter through the project’s task configuration and produced log output.