swoogo

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

• Third-party content exposure detected (high risk: 0.70). The skill's SKILL.md explicitly instructs the agent to use Membrane's proxy (e.g., "membrane request CONNECTION_ID /path/to/endpoint") and to run actions against the Swoogo API, which means the agent will fetch and interpret third-party Swoogo data (potentially user-generated/untrusted) as part of its workflow.