Threat
ngCERT GHOSTJACKING Advisory Formalizes Agentjacking — MCP Integrations Now a Government-Level Threat
Publication date unknown · Discovered yahoo.com
Page published
Publication date unknown · First observed: 20 Oct 2026
Coverage timeline
Single-source advisory — one report is available.
Why it matters
Ghostjacking can turn attacker-controlled integration data into authorized agent actions, making least-privilege configuration and separation of untrusted content from instructions important defenses.
An ngCERT advisory warns that Ghostjacking uses indirect prompt injection through MCP integrations to redirect AI agents’ authorized actions. The report describes demonstrations involving Cloudflare, Datadog, and Sentry, with potential impacts including domain hijacking, code execution, and cloud-credential theft, and identifies configuration hardening as a preventative measure.