CVE-2026-60086

Medium

Description

PraisonAI before 4.6.78 contains a prompt injection defense bypass vulnerability where the injection defense only blocks threats classified as CRITICAL, requiring three or more detector families to match simultaneously. Attackers can craft single or double-vector prompt injections that are classified as HIGH threat level and pass through unblocked to reach the model.

SeverityMedium

CVSS5.3

Exploit probability—

ProductPraisonai

PublishedJul 10, 2026

First seenJul 10, 2026

Weakness typeCWE-693CWE-693

How to fix

Update

praisonai4.6.78 or later

Vendor advisories

github.com/MervinPraison/PraisonAI/security/advisories/GHSA-4r3p-w3mc-5v34

Affected products

Product	Affected versions	Fixed in
praisonaiPyPI	v < 4.6.78	4.6.78

Check your version

Choose the product and enter the version you run to see whether it falls in the affected range.

In the Intelligence 360 plan

Attack Surface Management

See the assets tied to your domains, the technologies they run and known vulnerabilities in one list.