PraisonAI CLI automatically resolves @url mentions in prompt text and

Pydantic AI: SSRF cloud-metadata blocklist bypass via IPv4-mapped IPv6 (Incomplete

Apify Model Context Protocol (MCP) server: Domain Allowlist Bypass in

OpenClaw: Agent gateway config mutations could change protected operator settings

OpenClaw: CDP /json/version WebSocket URL could pivot to untrusted second

OpenClaw: Browser press/type interaction routes missed complete navigation guard coverage

OpenClaw vulnerable to SSRF in src/agents/tools/web-fetch.ts

TaskWeaver has Protection Mechanism Failure and Server-Side Request Forgery (SSRF

Langflow is a tool for building and deploying AI-powered

Penetration Testing of Agentic AI: A Comparative Security Analysis Across Models and Frameworks

system and 13 distinct attack scenarios that span prompt injection, Server Side Request Forgery (SSRF), SQL injection, and tool misuse. Our 130 total test cases reveal significant security disparities: AutoGen