CVE-2026-61439
HIGHDescription
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.
Is your site exposed to CVE-2026-61439?
Run a free security scan — no signup, results in seconds.
CVSS v3.1 Score
EPSS — Exploit Prediction
EPSS estimates the probability that this vulnerability will be exploited in the wild within the next 30 days. A higher score means more likely to be exploited.
Weakness Type (CWE)
References
Frequently Asked Questions
What is CVE-2026-61439? +
How severe is CVE-2026-61439? +
How do I check if I'm vulnerable to CVE-2026-61439? +
Related Vulnerabilities
CWE-1188 Initialization of a Resource with an Insecure Default vulnerability exists that could cause unauthorized disclosure of sensitive information when …
An Exposure of Sensitive System Information to an Unauthorized Control Sphere and Initialization of a Resource with an Insecure Default …
Enabled IP Forwarding feature in B&R Automation Runtime versions before 6.0.2 may allow remote attack-ers to compromise network security by …
A security issue exists due to the web-based debugger agent enabled on Rockwell Automation ControlLogix® Ethernet Modules. If a specific …
Filament is a collection of full-stack components for accelerated Laravel development. All Filament features that interact with storage use the …
A configuration weakness in the device’s remote management service allows an authenticated session to be established over a communication channel …