make-module-configuring

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly maps external webhook input into the AI agent (see examples/ai-agent-full-blueprint.json: gateway:CustomWebHook module id 1 feeding "{{1.message}}" into the ai-local-agent module and ai-agents.md describing the agent's message field), meaning arbitrary untrusted HTTP payloads can be ingested and directly influence the agent's decisions and tool invocations.