memsource

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly uses Membrane to run actions and proxy arbitrary requests to the Memsource API (see "membrane action run ..." and "membrane request CONNECTION_ID /path/to/endpoint" in SKILL.md), which causes the agent to fetch and interpret third-party Memsource data (potentially user-generated) as part of its workflow and could therefore allow indirect prompt-injection.