CVE-2026-44336Disclosure(praison / praisonai)

LOWCVSS 9.6 · CRITICAL

Signal is active with 1 mentions in latest observed window

Immediate actions

Track advisory updates for patch or workaround availability

Recommended action window: Monitor and triage in normal cycle

NVD description

PraisonAI is a multi-agent teams system. Prior to version 4.6.34, PraisonAI's MCP (Model Context Protocol) server (praisonai mcp serve) registers four file-handling tools by default — praisonai.rules.create, praisonai.rules.show, praisonai.rules.delete, and praisonai.workflow.show. Each accepts a path or filename string from MCP tools/call arguments and joins it onto ~/.praison/rules/ (or, for workflow.show, accepts an absolute path) with no containment check. The JSON-RPC dispatcher passes params["arguments"] blind to each handler via **kwargs without validating against the advertised input schema. By setting rule_name="../../<some-path>" an attacker walks out of the rules directory and writes any file the running user can write. Dropping a Python .pth file into the user site-packages directory escalates this primitive to arbitrary code execution in any subsequent Python process the user spawns — the next praisonai CLI invocation, an IDE script run, the user's python REPL, or any background Python service. This issue has been patched in version 4.6.34.

praison CVEs Back to dashboard

0.0/ 10 priority

Sources & remediation

Exploit / PoC references

Weakness type (CWE)

CWE-20CWE-22CWE-94CWE-829CWE-913

Priority

LOW

Exploitation

NONE

PoC

YES

Patch

NONE

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

8 mentions across 4 observed days
Momentum state: stable

What's happening

Technical details provided in 5 signals
Disclosure: 5 classified signals
General: 3 classified signals
Peaked 2d ago at 5 mentions (2026-05-14); latest day: 1
8 total mentions across 4 days

Affected systems

Vendors

praison

Products

praisonai

Deep dive

Activity timeline8 mentions / 4d

Signal classification2 categories

Disclosure

562.5%

General

337.5%

Referenced assets3 URLs

By indicator

Classification over time

Date	Total	Labels

2026-05-08	1	General1
2026-05-14	5	Disclosure4General1
2026-06-16	1	Disclosure1
2026-07-21	1	General1

Full discourse8 posts

CVE@CVEnew81d
General
CVE-2026-47394 PraisonAI is a multi-agent teams system. Prior to version 4.6.40, the fix for GHSA-9mqq-jqxf-grvw / CVE-2026-44336 is incomplete. The original advisory description na… https://www.cve.org/CVERecord?id=CVE-2026-47394
Post summary
The notice mentions CVE-2026-47394 in the context of PraisonAI’s versioning and an incomplete fix for a related CVE, but offers no PoC, exploit details, patch information, or technical vulnerability specifics.
00020871
58.1K followersView on X
Joey Romaine 🇺🇸 |=★=|@Tank23x0116d
Disclosure
CVE-2026-44336: critical severity (CVSS 9.6). Scope affected systems for a remote code execution issue. Scope it today so nobody has to explain it tomorrow.
Post summary
The text announces CVE-2026-44336 as a critical remote code execution vulnerability with CVSS 9.6, but provides no further detail on exploitation, patches, or proof of concept.
1000048
337 followersView on X
Lyrie.ai@lyrie_ai149d
Disclosure
--- Validated by the Lyrie Threat Intelligence Pipeline — 3 independent sources confirmed before publication. No speculation. CVE: CVE-2026-44336 CVSS: 9.6 (3.1) — CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H Severity: CRITICAL Status: Critical advisory
Post summary
The text announces a critical advisory for CVE‑2026‑44336, listing its CVSS score of 9.6 and associated severity information.
1000039
210 followersView on X
Lyrie.ai@lyrie_ai149d
Disclosure
References CVE: CVE-2026-44336 CVSS: 9.6 (3.1) — CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H Severity: CRITICAL Status: Critical advisory
Post summary
The advisory announces CVE-2026-44336 with a critical CVSS score of 9.6, indicating severe confidentiality, integrity, and availability impact, but provides no further details on exploitation or mitigation.
1000027
210 followersView on X
Lyrie.ai@lyrie_ai149d
Disclosure
CRITICAL: CVE-2026-44336 (CVSS 9.6) — praison praisonai. CVE: CVE-2026-44336 CVSS: 9.6 (3.1) — CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H Severity: CRITICAL Status: Critical advisory
Post summary
The message announces CVE‑2026‑44336, a critical vulnerability with detailed CVSS metrics, but does not mention a PoC, exploit code, active exploitation, patch, or false positive claim.
1000031
210 followersView on X
Lyrie.ai@lyrie_ai149d
Disclosure
CVE: CVE-2026-44336 CVSS: 9.6 (3.1) — CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H Severity: CRITICAL Status: Critical advisory PraisonAI is a multi-agent teams system.
Post summary
CVE-2026-44336 is a newly disclosed critical vulnerability with a CVSS score of 9.6, but no PoC, exploit, or patch information is provided.
1000032
210 followersView on X
Lyrie.ai@lyrie_ai149d
General
https://lyrie.ai/research/research/cve-2026-44336-praison-praisonai #lyrie #cybersecurity #CVE #threatintel #zerodayattack
Post summary
The tweet shares a link to a research page on CVE‑2026‑44336 without providing additional context or specific details.
0000016
210 followersView on X
CVE@CVEnew155d
General
CVE-2026-44336 PraisonAI is a multi-agent teams system. Prior to version 4.6.34, PraisonAI's MCP (Model Context Protocol) server (praisonai mcp serve) registers four file-handling t… https://www.cve.org/CVERecord?id=CVE-2026-44336
Post summary
The passage notes a file‑handling issue in PraisonAI's MCP server before version 4.6.34 and links to the CVE record, but provides no information on exploits, patches, or detailed technical aspects.
00000123
57.5K 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-2026-44336

Joey Romaine 🇺🇸 |=★=|[verified]@Tank23x0Disclosure

The text announces CVE-2026-44336 as a critical remote code execution vulnerability with CVSS 9.6, but provides no further detail on exploitation, patches, or proof of concept.

Lyrie.ai[verified]@lyrie_aiDisclosure

The text announces a critical advisory for CVE‑2026‑44336, listing its CVSS score of 9.6 and associated severity information.

Lyrie.ai[verified]@lyrie_aiDisclosure

The advisory announces CVE-2026-44336 with a critical CVSS score of 9.6, indicating severe confidentiality, integrity, and availability impact, but provides no further details on exploitation or mitigation.

Lyrie.ai[verified]@lyrie_aiDisclosure

The message announces CVE‑2026‑44336, a critical vulnerability with detailed CVSS metrics, but does not mention a PoC, exploit code, active exploitation, patch, or false positive claim.

Lyrie.ai[verified]@lyrie_aiDisclosure

CVE-2026-44336 is a newly disclosed critical vulnerability with a CVSS score of 9.6, but no PoC, exploit, or patch information is provided.

Lyrie.ai[verified]@lyrie_aiGeneral

The tweet shares a link to a research page on CVE‑2026‑44336 without providing additional context or specific details.

CVE@CVEnewGeneral

The notice mentions CVE-2026-47394 in the context of PraisonAI’s versioning and an incomplete fix for a related CVE, but offers no PoC, exploit details, patch information, or technical vulnerability specifics.

CVE@CVEnewGeneral

The passage notes a file‑handling issue in PraisonAI's MCP server before version 4.6.34 and links to the CVE record, but provides no information on exploits, patches, or detailed technical aspects.