CVE-2026-61439

highCVSS 7.5covered by 1 sourcefirst seen 2026-07-11

PraisonAI versions before 4.6.78 contain a prompt injection defense misconfiguration where the block threshold defaults to CRITICAL severity, allowing HIGH-level threats to pass through unblocked. Attackers can submit single-vector prompt injection attacks such as instruction overrides or financial manipulation that trigger HIGH severity detection but are logged without blocking, enabling system prompt extraction and unauthorized tool invocations.

⚡ Watch CVE-2026-61439

Get an email if CVE-2026-61439 is added to CISA KEV, gains public exploit code, or a new advisory cites it — max one per day, one-click unsubscribe.

Advisory coverage (1)

highCVE-2026-61439: PraisonAI versions before 4.6.78 contain a prompt injection defense misconfiguration where the…nvd · 2026-07-11

External references

NVD record for CVE-2026-61439

CVE.org record

Embed the live status

— this badge updates automatically when the KEV or exploit status changes. How to embed it →

[![CVE-2026-61439 status](https://www.csirts.com/badge/CVE-2026-61439)](https://www.csirts.com/cve/CVE-2026-61439)