building-workflows

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

• Third-party content exposure detected (medium risk: 0.30). The skill instructs the agent to read workflow execution logs, past run invocations, and triggering payloads using MCP tools like workflows-logs, workflows-get-invocation, and workflows-list-invocations, which can contain outsider-submitted event properties and webhook/event data.