CVE-2026-57138
From 1.4.0 until 1.7.2, codeMode in src/praisonai-ts/src/tools/builtins/code-mode.ts executes untrusted JavaScript with new Function() inside with(sandbox) and relies on a small source-code blocklist plus shadowed process and require properties.
Does this matter?
High impact if exploited, but EPSS currently rates exploitation as unlikely (0.39%). Schedule it in the normal patch cycle and watch for a rise in EPSS or a public exploit.
Description
PraisonAI is a multi-agent teams system. From 1.4.0 until 1.7.2, codeMode in src/praisonai-ts/src/tools/builtins/code-mode.ts executes untrusted JavaScript with new Function() inside with(sandbox) and relies on a small source-code blocklist plus shadowed process and require properties. Code can use ({}).constructor.constructor to recover the real Function constructor, obtain process and process.mainModule.require, and reach host filesystem and subprocess APIs despite the advertised sandbox. Attackers who control codeMode input can read secrets, modify files, execute commands, or exhaust the host process. This issue is fixed in version 1.7.2.
- CVSS 3.1
- 9.9 CRITICALCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H
- EPSS
- 0.39% probability · 33th percentile
- Public exploits
- None in Exploit-DB
- CISA KEV
- Not listed
- Weakness
- CWE-184, CWE-693
- Source
- security-advisories@github.com
EPSS 0.4% since 19 September 2026; no change recorded yet. Points are recorded when the score first appears and whenever it moves by a percentage point or more.
References
- https://github.com/MervinPraison/PraisonAI/commit/709a0387853709a5e2f2c34680fa64cada252c27
- https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.60
- https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-vmmj-pfw7-fjwp
- https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-vmmj-pfw7-fjwp
Source: NVD record, EPSS from FIRST.org, KEV from CISA, exploits from Exploit-DB. Refreshed daily. Download this record as JSON.