NVD / CVE Program· CNA GitHub_M

CVE-2026-40088: Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection') in praisonai

CriticalCVSS 9.6 · v3.1—No exploit Fix available

Noroxi assessment

Priority: Monitor (action score 38/100)

The sources we track (CISA KEV, Exploit-DB, Metasploit, Nuclei, GitHub) show no public exploit code or exploitation in the wild.
Probability of exploitation in the next 30 days: 0.42% (FIRST EPSS).
Anyone who can reach it over the internet can trigger it. No account or password is required. A user must open a link or visit a page. No special conditions are required; it is repeatable.
Fixed version: MervinPraison PraisonAI 4.5.121.

Low priority for now. Upgrade to MervinPraison PraisonAI 4.5.121 or later.

Generated automatically from the record's data: CVSS (NVD and CNA), CISA KEV and SSVC, FIRST EPSS, exploit sources, fixed versions. How we calculate it

Primary sources: NVD · CVE.org · FIRST EPSS

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.

Published: Apr 9, 2026
Updated: Oct 25, 2026
EPSS: 0.4% · 37th percentile
CWE: CWE-78

Report tools

JSON

Action score

Monitor

Low priority for now.

CVSS: 38 / 40 · 9.6 / 10
CISA KEV: 0 / 30 · Not listed
EPSS: 0 / 30 · 0.4%

CISA SSVC decision

Exploitation: proof of concept
Automatable: no
Technical impact: total

Vulnrichment: CISA's decision-tree inputs.

CNA vs NVD score

NVD: 9.6
CNA · GitHub_M: 9.6; agree

The score given by the assigning authority versus NVD’s independent score. A gap means the severity is contested.

Get told when this record changes

Not in KEV: no record of exploitation in the wild
No public exploit code on record
A fix has been released

If any of these changes, we'll tell you in the daily email digest.

Is your version affected? Check it

Noroxi analysis

What does it mean in your environment?

The assessment above is generated automatically from the record's data; it doesn't know your environment. Our team verifies on your systems whether this vulnerability is actually exploitable and which mitigation is enough.

We use this product, ask for help

Affected systems

Is your version affected?

Pick the product and type the version you run. It's compared with this record's version ranges in your browser; the version isn't sent anywhere.

Vendor	Product	CPE
praison	praisonai	cpe:2.3:a:praison:praisonai

Versions reported by the vendor

Affected version ranges reported by the assigning authority (GitHub_M). Independent of NVD's CPE analysis and usually ahead of it.

MervinPraison PraisonAI
- < 4.5.121affected

Affected versions

NVD version ranges (for catalog products). Add the product to your stack with a version and matching uses these.

praison praisonaibefore 4.5.121

Package-level exposure

OSV and GitHub Advisory data: ecosystem, package and range. SBOM matching uses this table.

Ecosystem	Package	Affected range	Fix
PyPI	praisonai	before 4.5.121	4.5.121

Same product

praison: all records

Other highest-scoring records for the same primary product.

CVE-2026-40114PraisonAI has Server-Side Request Forgery via Unvalidated webhook_url in Jobs API
40Plan
CVE-2026-39305Arbitrary File Write / Path Traversal in Action Orchestrator
40Plan
CVE-2026-34955PraisonAI: Sandbox Escape via shell=True and Bypassable Blocklist in SubprocessSandbox
40Plan

Published before and after this one in the same product

← EarlierCVE-2026-39890Apr 8, 2026 · PraisonAI Affected by Remote Code Execution via YAML Deserialization in Agent Definition Loading
39Monitor
← EarlierCVE-2026-39891Apr 8, 2026 · PraisonAI has a Template Injection in Agent Tool Definitions
35Monitor
Later →CVE-2026-40112Apr 9, 2026 · PraisonAI has Stored XSS via Unsanitized Agent Output in HTML Rendering (nh3 Not a Required Dependency)
24Monitor

Remediation

Which version to upgrade to

Fix versions compiled from the vendor, package registries and Microsoft. Verify the vendor's note before upgrading.

Product / package	Fixed version	Source
MervinPraison PraisonAI	4.5.121 · description	Vendor (CNA)
PyPI:praisonai	4.5.121	Package registry (OSV)

Exploit status

No known public exploit

No public exploit has been observed yet. That doesn't mean you're safe, only that the bar is a little higher.

Research context

For pentesters and researchers: attack profile, score disagreement, timeline, patch commits, credits, variant and chain candidates, bug bounty scope. All derived from existing data; no exploit code.

Timeline

From publication to today: proof of concept, Metasploit module, CISA KEV and fix record. Dates are as reported by the sources.

No dated events beyond publication.

Variant candidates

Same product, same weakness class, within 18 months. If the patch missed the root cause, the sibling bug is here.

CVE-2026-349556 days apartPraisonAI: Sandbox Escape via shell=True and Bypassable Blocklist in SubprocessSandbox
40Plan
CVE-2026-402885 days apartPraisonAI: Critical RCE via `type: job` workflow YAML
39Monitor
CVE-2026-349356 days apartPraisonAI: OS Command Injection in MCPHandler.parse_mcp_command()
39Monitor

Not on record for this CVE: EPSS history · patch commit or PR link · researcher credit · public bounty program.

Technical details

Attack conditions

Anyone who can reach it over the internet can trigger it.
No account or password is required.
A user must open a link or visit a page.
No special conditions are required; it is repeatable.

If successful

Confidentiality: high · data can be read
Integrity: high · data or configuration can be modified
Availability: high · the service can be disrupted

Impact can extend beyond the vulnerable component (scope changes).

Attack vector: Network
Attack complexity: Low
Privileges required: None
User interaction: Required
Scope: Changed
Confidentiality impact: High
Integrity impact: High
Availability impact: High

Weakness class (CWE)

CWE-78 · Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')

CVSS vector

CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H

nvd-primary

Root cause

User input is inserted as text into a shell command. The shell may interpret special characters in the input as part of the command.

The bug in code

The whole CWE-78 class

A representative example of this vulnerability class. Not the vendor's source code; it shows the faulty pattern and its fix.

Vulnerable

1const host = req.body.host;
2exec("ping -c 1 " + host, onResult);

Fixed

1const host = req.body.host;
2if (!/^[a-z0-9.-]{1,253}$/i.test(host)) return res.sendStatus(400);
3execFile("ping", ["-c", "1", host], onResult);

Attack context

MITRE CAPEC attack patterns and ATT&CK techniques for this weakness class (CWE). A starting point for detection rules and threat hunting.

Attack patterns (CAPEC)

ATT&CK techniques

—

Change log (1)

Fix✗ → ✓Sep 28, 2026, 10:48 PM UTC

For records you follow, these changes also arrive as notifications. →

References

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

Vendor advisories and official records. Exploit/PoC links are deliberately left out.

All records