CVE-2026-77177: Open GenAI Stack prompt injection in Meta AI backend

Open GenAI Stack (ogx-ai) allows code execution through unsanitized prompt injection using Jinja2 template syntax in Meta AI backends for WhatsApp and other products. The vulnerability enables server-side expression evaluation without proper input sanitization.

Occurred 11 June 2026 · Disclosed 29 September 2026 · Record updated 1 October 2026

Impact

Code execution on Meta AI backend systems used in WhatsApp and other products

Our coverage

A keyhole-sized crack in a metal vault's door reveals gears spinning backward as invisible hands manipulate the internal mechanisms from outside.

Vulnerabilities

Prompt injection flaw reported in Meta's Open GenAI Stack

A CVE published on 29 September 2026 says template syntax in prompts could be evaluated on the server, allowing code execution.

29 Sept 2026

Sources

nvd.nist.govhttps://nvd.nist.gov/vuln/detail/CVE-2026-77177