Vulnerability details

CVE-2026-61439

MervinPraison PraisonAI

PraisonAI before 4.6.78 Prompt Injection Defense Bypass

CVSS 4.0
8.7High

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.

CVSS scores

ScoreVersionSourceVector
8.7High 4.0 CVEProject cvelistV5 (CNA) (VulnCheck) CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N
7.5High 3.1 CVEProject cvelistV5 (CNA) (VulnCheck) CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N

Affected products

VendorProductVersionsSource
MervinPraison PraisonAI v < 4.6.78 CVEProject cvelistV5 (CNA)

References and advisories

2
Kolun on Telegram @kolunsec Exploited CVEs, key news and a daily digest Alerts for this product's next CVEsFollow the product to get new vulnerabilities on Telegram.

Details

Published
2026-07-11
Last updated
2026-07-14
State
Published
Assigner (CNA)
VulnCheck

Exploit prediction (EPSS)

0.34%
Probability of exploitation in 30 days
27.7%
Percentile (among all CVEs)

SSVC assessment (CISA)

Automatable
Yes
Exploitation
Proof of concept
Technical impact
Partial

Weaknesses (CWE)

  • CWE-1188
    Initialization of a Resource with an Insecure Default