CVE-2026-61439 PraisonAI before 4.6.78 Prompt Injection Defense Bypass
Attackers can bypass prompt injection defenses in PraisonAI to extract system prompts and invoke unauthorized tools due to a misconfigured blocking threshold.
- Exploited in the wild
- Not known
- Login needed
- Not needed
- Attackable
- Over the internet
- Victim action needed
- Not needed
- Fix
- Available
What is CVE-2026-61439?
CVE-2026-61439 is a high-severity vulnerability in MervinPraison PraisonAI, published on 11 Jul 2026. An attacker can exploit it over the internet without logging in, with no action from the victim.
Official description
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.
Weakness: CWE-1188
Which versions are affected by CVE-2026-61439?
3 open source packages ship an affected version, including praisonai and PraisonAI.
| Package | Affected | Fixed in |
|---|---|---|
praisonai PyPI | All versions | 4.6.78 |
praisonai PyPI | All versions | 4.6.78 |
PraisonAI PyPI | All versions | 4.6.78 |
How do I fix CVE-2026-61439?
Upgrade praisonai to 4.6.78 or later.
Is CVE-2026-61439 being exploited?
It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-61439 exists.
Sources
Also known as GHSA-fj8f-m44g-c479, PYSEC-2026-4255.