CVE-2026-61439
published 2026-07-11CVE-2026-61439: PraisonAI versions before 4.6.78 contain a prompt injection defense misconfiguration where the block threshold defaults to CRITICAL severity, allowing…
PriorityP345high7.5CVSS 3.1
AVNACLPRNUINSUCHINAN
EPSS
0.43%
37.0th percentile
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.
Affected
1 ranges
| Vendor | Product | Version range | Fixed in |
|---|---|---|---|
| mervinpraison | praisonai | < 4.6.78 | 4.6.78 |
CVSS provenance
nvdv3.17.5HIGHCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N
nvdv4.08.7HIGHCVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
Stop checking back — get the weekly exploitation signal.
Every Monday: what got weaponized or added to CISA KEV in the last seven days — each CVE cross-linked to its PoC, Nuclei template, and detection rule. Free, one email a week, unsubscribe in one click.
GHSA
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.
ghsa_unreviewed·2026-07-11
CVE-2026-61439 [HIGH] CWE-1188 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.
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.
VulDB
MervinPraison PraisonAI up to 4.6.77 Prompt Injection Defense injection (EUVD-2026-43179)
vuldb·2026-07-11·CVSS 7.5
CVE-2026-61439 [HIGH] MervinPraison PraisonAI up to 4.6.77 Prompt Injection Defense injection (EUVD-2026-43179)
A vulnerability, which was classified as critical, was found in MervinPraison PraisonAI up to 4.6.77. This vulnerability affects unknown code of the component Prompt Injection Defense. The manipulation results in injection.
This vulnerability is known as CVE-2026-61439. It is possible to launch the attack remotely. No exploit is available.
No detection rules found.
No public exploits indexed.
No writeups or analysis indexed.
2026-07-11
Published