> CVE-2026-57137 [HIGH]

« BACK_TO_HOME
PUBLISHED
2026-09-15 11:17
MODIFIED
2026-09-15 11:17
CVSS_SCORE V3
8.8
EPSS (Prob. Exploit)
0.51%
Top 58.1%
DATA SOURCES:
NVD đź”— 2026-09-15 CWE MITRE đź”— 2026-10-01 FIRST EPSS đź”— 2026-10-18 GITHUB đź”— 2026-10-15 OSV đź”— 2026-10-26

> DESCRIPTION

PraisonAI is a multi-agent teams system. From 1.4.0 until 1.7.2, createAgentLoop() in src/praisonai-ts/src/ai/agent-loop.ts passes executable tools to generateText() before invoking the onToolCall approval callback. Because the wrapped AI SDK executes tool handlers during generation, a callback that returns false records tool_rejected only after the denied tool has already produced side effects and populated toolResults. Applications using onToolCall as a human or policy approval boundary can therefore execute rejected file, command, API, or data-modifying operations. This issue is fixed in version 1.7.2.

> AFFECTED_PRODUCTS

ℹ️ Aucun produit affecté n'a encore été publié par NVD pour cette CVE.

> CVSS V3 METRICS

CVSS_VECTOR
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
EXPLOITABILITY
2.8
IMPACT
5.9

> MÉTRIQUES CVSS DÉTAILLÉES

CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Métrique Valeur Interprétation
AV (Vecteur d'Attaque)
Attack Vector
Network (N)
Exploit possible à distance via réseau (HTTP, API, etc.)
AC (Complexité d'Attaque)
Attack Complexity
Low (L)
Peu de conditions requises pour exploiter
PR (Privilèges Requis)
Privileges Required
Low (L)
Authentifié avec compte utilisateur basique
UI (Interaction Utilisateur)
User Interaction
None (N)
Aucune interaction utilisateur nécessaire
S (Périmètre)
Scope
Unchanged (U)
Impact reste dans le périmètre du composant compromis
C (Impact Confidentialité)
Confidentiality Impact
High (H)
Divulgation totale d'informations
I (Impact Intégrité)
Integrity Impact
High (H)
Modification totale des données possible
A (Impact Disponibilité)
Availability Impact
High (H)
Interruption totale du service possible

> RÉSUMÉ DES IMPACTS

Confidentialité
High
Divulgation totale d'informations
Intégrité
High
Modification totale des données possible
Disponibilité
High
Interruption totale du service possible

> WEAKNESSES

CWE-693 CWE-862 CWE-863

> CWE DETAILED DESCRIPTIONS

CWE-693: Protection Mechanism Failure - The product does not use or incorrectly uses a protection mechanism that provides sufficient defense against directed attacks against the product. | CWE-862: Missing Authorization - The product does not perform an authorization check when an actor attempts to access a resource or perform an action. | CWE-863: Incorrect Authorization - The product performs an authorization check when an actor attempts to access a resource or perform an action, but it does not correctly perform the check.

> GITHUB SECURITY ADVISORY

GHSA-h2w2-v7j6-xqm4 HIGH

npm PraisonAI AgentLoop onToolCall approval runs after tool execution

AFFECTED PACKAGES:
NPM / praisonai
>= 1.4.0, <= 1.7.1
Fixed in: 1.7.2

> OSV (GOOGLE OPEN SOURCE VULNERABILITIES)

PraisonAI AgentLoop onToolCall approval runs after tool execution

AFFECTED PACKAGES:
Unknown / Unknown
584 versions affected
ALIASES:
GHSA-h2w2-v7j6-xqm4

> HISTORIQUE DES MODIFICATIONS

Première apparition
15/09/2026 11:17
Source: NVD
đź“Š ENRICHISSEMENT 01/10/2026 06:01
CWE
Champ modifié: Description CWE
Ancienne valeur:
N/A
Nouvelle valeur:
CWE-693: Protection Mechanism Failure - The product does not use or incorrectly uses a protection mechanism that provides sufficient defense against directed attacks against the product. | CWE-862: Mi...
Total des modifications: 1 Dernière mise à jour: 3 weeks ago

> REFERENCES

https://github.com/MervinPraison/PraisonAI/commit/6b4b59fbe71a74983626c7a0cf7e10...
https://github.com/MervinPraison/PraisonAI/releases/tag/v4.6.62
https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-h2w2-v7j6-xq...
« BACK_TO_HOME