activepieces-expert

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow (references/ai-and-agents.md and references/pieces-usage.md) explicitly describes agent orchestration and use of the HTTP/connector pieces and webhook triggers to fetch arbitrary external data (e.g., public URLs, SaaS connectors, webhooks) which the LLM reads and can use to drive tool calls and next actions, exposing it to untrusted third-party content.