automate-whatsapp

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly documents agent node webhook tools (references/node-types.md, "flow_agent_webhooks") that let an agent call arbitrary external HTTP URLs and ingest/parse their JSON responses (including jmespath_query), which the agent can use to set vars or drive decisions—exposing it to untrusted third-party content that could carry indirect prompt-injection instructions.