The Wire.Tracking threats to Agents 312 raw → 45 curated · updated 27 Jun 2026

Incident · curated 27 Jun 2026

Millions of AI agents imperiled by critical vulnerability in open source package - Ars Technica

First reported 28 May 2026 · 30d ago

Coverage timeline

28 May 2026

Single-source incident — first reported, latest, and curated coincide.

MCP servers store credentials for AI agents' external accounts, so a trivially exploitable auth bypass in their underlying framework hands attackers a high-value path to mailbox access, PII, RCE, and credential theft across the Python AI tooling ecosystem.

A critical authentication-bypass vulnerability (CVE-2026-48710, dubbed BadHost) in the Starlette framework lets a single character injected into the HTTP Host header bypass path-based authorization. Because Starlette underpins FastAPI, vLLM, LiteLLM, and many MCP servers and agent harnesses, the flaw exposes millions of AI agents and their stored third-party credentials and sensitive data to trivial exploitation.

Why it matters

MCP servers store credentials for AI agents' external accounts, so a trivially exploitable auth bypass in their underlying framework hands attackers a high-value path to mailbox access, PII, RCE, and credential theft across the Python AI tooling ecosystem.

Curated from sources around the web.
Permalinks stay valid even if an incident is later merged.   Feed · Search · API docs · RSS