PraisonAI: Remote Code Execution via Sandbox Escape in `codeMode` Tool

published 2026-06-18 4 mo ago modified 2026-09-15 54 d ago also EUVD-2026-78423 , GHSA-p69m-4f92-2v84

cvss: 9.8; version 3.1, CNA
cisa kev: Not listed; not in CISA's catalog
epss: 0.7%; EPSS 0.7% chance of exploitation in 30 days, percentile 55%
public exploits: 0; none known

PraisonAI is a multi-agent teams system. Prior to 1.7.2, the codeMode tool in src/praisonai-ts/src/tools/builtins/code-mode.ts executes model-generated JavaScript with new Function() and with(sandbox), while a regular-expression blocklist can be bypassed with Function('return this')() to recover the global object and by constructing the child_process module name dynamically. An attacker who can influence the code argument can access host process capabilities, read or write files, obtain environment credentials, and execute operating-system commands with the PraisonAI process privileges. This issue is fixed in version 1.7.2.

Patch / fix

fixed in 2 links 2

npm praisonai 1.7.2
praison praisonai 1.7.2

CISA SSVC

Exploitation: none
Automatable: yes
Technical impact: total
Assessed: 55 d ago (2026-09-15)

Exploit prediction

0.74% chance of exploitation in the next 30 days, higher than 55% of all scored CVEs (FIRST EPSS, 2026-11-08).

CVSS scores

assigned by	version	score	vector
CNA	3.1	9.8	CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
GitHub	3.1	9.8	CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

Affected packages

ecosystem	package	affected	fixed in
npm	praisonai	<1.7.2	1.7.2

Affected products

MervinPraison PraisonAI

Classification

Weakness

CWE-94 Improper Control of Generation of Code

References

Sources

Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.

CPEs and fixed versions use Anchore's correction of NVD's data: Added CPE configurations because not yet analyzed by NVD.

Summary