CVE-2026-40088Disclosure(praison / praisonai)

LOWCVSS 9.6 · CRITICAL

Signal is active with 1 mentions in latest observed window

Immediate actions

Patch praison praisonai systems immediately

Recommended action window: Monitor and triage in normal cycle

NVD description

PraisonAI is a multi-agent teams system. Prior to 4.5.121, the execute_command function and workflow shell execution are exposed to user-controlled input via agent workflows, YAML definitions, and LLM-generated tool calls, allowing attackers to inject arbitrary shell commands through shell metacharacters. This vulnerability is fixed in 4.5.121.

praison CVEs Back to dashboard

0.5/ 10 priority

Sources & remediation

Exploit / PoC references

https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-2763-cj5r-c79m

Other references

https://github.com/MervinPraison/PraisonAI/releases/tag/v4.5.121

Weakness type (CWE)

CWE-78

Priority

LOW

Exploitation

NONE

PoC

YES

Patch

AVAILABLE

Momentum

STABLE

Are you affected?

If you run products in this scope, you should treat this CVE as relevant to your environment.

praisonai

Threat summary

Patch or workaround signal is available
5 mentions across 3 observed days
Momentum state: stable

What's happening

Patch or workaround mentioned in 1 signal
Technical details provided in 5 signals
Disclosure: 3 classified signals
General: 1 classified signal
Peaked 2d ago at 3 mentions (2026-04-09); latest day: 1
5 total mentions across 3 days

Affected systems

Vendors

praison

Products

praisonai

Deep dive

Activity timeline5 mentions / 3d

Signal classification3 categories

Disclosure

360.0%

General

120.0%

Patch

120.0%

Referenced assets5 URLs

By indicator

Classification over time

Date	Total	Labels

2026-04-09	3	Disclosure1General1Patch1
2026-04-10	1	Disclosure1
2026-04-11	1	Disclosure1

Full discourse5 posts

CCB Alert@CCBalert182d
Disclosure
Warning: Multiple Critical vulnerabilities in #PraisonAI. e.g. CVE-2026-40088 and CVE-2026-40154 CVSS: 9.6. These vulnerabilities can lead to remote code execution #RCE in various different ways! More info: https://github.com/MervinPraison/PraisonAI/security #Patch #Patch #Patch
Post summary
The post alerts readers to two newly identified high‑severity CVEs (CVE‑2026‑40088, CVE‑2026‑40154) in PrinzAI that allow remote code execution, but it does not provide any proofs of exploitation or patch details.
00002235
7.2K followersView on X
PulsePatch.io@pulsepatchio181d
Disclosure
`PraisonAI` is affected by CVE-2026-40088, a critical OS Command Injection vulnerability. This flaw could enable arbitrary command execution. Monitor for security updates. #PraisonAI #OSCommandInjection #infosec https://www.pulsepatch.io/posts/cve-2026-40088-praisonai-os-command-injection
Post summary
The tweet announces that PraisonAI is affected by CVE-2026-40088, a critical OS command injection vulnerability enabling arbitrary command execution, and advises monitoring for updates, without providing PoC, exploit code, or patch details.
0000050
11 followersView on X
CVEFind.com@CveFindCom182d
Patch
[CVE-2026-40088: CRITICAL] Critical cybersecurity update: PraisonAI fixed a vulnerability in version 4.5.121 that allowed attackers to inject shell commands via user-controlled input. Update now to stay secure.#cve,CVE-2026-40088,#cybersecurity https://cvefind.com/CVE-2026-40088
Post summary
The post announces that PraisonAI has released a patch for CVE‑2026‑40088, detailing a shell‑command injection flaw and urging users to update to mitigate the risk.
0000033
619 followersView on X
CVE@CVEnew182d
General
CVE-2026-40088 PraisonAI is a multi-agent teams system. Prior to 4.5.121, the execute_command function and workflow shell execution are exposed to user-controlled input via agent wo… https://www.cve.org/CVERecord?id=CVE-2026-40088
Post summary
The message announces CVE‑2026‑40088 for PraisonAI, highlighting a command injection flaw in execute_command and workflow shell execution, but provides no PoC, exploit, or patch details.
0000090
57.0K followersView on X
0day Signal@0dayPublishing182d
Disclosure
🚨 CVE-2026-40088: Impro... LLM-generated tool calls executing shell commands without sanitization = RCE paradise for prompt injection attacks. #CVE202640088 #RCE #AIHacking. https://zerodaysignal.com/vulnerability/CVE-2026-40088 #netsec #vulnerability #CVE #sysadmin #zeroday
Post summary
CVE-2026-40088 allows remote code execution via unsanitized LLM‑generated tool calls; no PoC, exploitation, or patch details are provided in the brief announcement.
0000073
204 followersView on X

CPE platform detail1 entries

Part:

Vendor:

Product:

Version:

Target SW:

Target HW:

1 of 1 entries

Part	Vendor	Product	Version	Target SW	Target HW
App	praison	praisonai	-	-	-

Explore more

Back to dashboard praison CVEs praisonai vulnerabilities

What researchers are saying

CVE-2026-40088

CCB Alert@CCBalertDisclosure

The post alerts readers to two newly identified high‑severity CVEs (CVE‑2026‑40088, CVE‑2026‑40154) in PrinzAI that allow remote code execution, but it does not provide any proofs of exploitation or patch details.

PulsePatch.io@pulsepatchioDisclosure

The tweet announces that PraisonAI is affected by CVE-2026-40088, a critical OS command injection vulnerability enabling arbitrary command execution, and advises monitoring for updates, without providing PoC, exploit code, or patch details.

CVEFind.com@CveFindComPatch

The post announces that PraisonAI has released a patch for CVE‑2026‑40088, detailing a shell‑command injection flaw and urging users to update to mitigate the risk.

CVE@CVEnewGeneral

The message announces CVE‑2026‑40088 for PraisonAI, highlighting a command injection flaw in execute_command and workflow shell execution, but provides no PoC, exploit, or patch details.

0day Signal@0dayPublishingDisclosure

CVE-2026-40088 allows remote code execution via unsanitized LLM‑generated tool calls; no PoC, exploitation, or patch details are provided in the brief announcement.