autogpt-agents

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly exposes and consumes external/untrusted content via Integration Blocks (GitHub, Discord, Notion, HTTP request blocks) and webhook handlers that parse incoming payloads and feed them into agent graphs (see "Integration Blocks" and "Webhook handling" in SKILL.md and references/advanced-usage.md), meaning user-generated or public third‑party content can be read and materially influence agent decisions and tool use.