CVE-2026-55522
PraisonAI workflow include bypasses tools.py autoload opt-in and executes included recipe code
Texto original en inglés · Ver en español
CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H
Fuente: CNA
Ciclo de vida de la vulnerabilidad
| Fecha | Fase | Evento | Detalle |
|---|---|---|---|
| Remediación | Parche 1.6.58 | praisonaiagents · -53 d desde divulgación | |
| Remediación | Parche 4.6.58 | praisonai · -53 d desde divulgación | |
| Divulgación | Publicada | CVE-2026-55522 divulgada · CVSS 7.8 (CNA) | |
| Divulgación | Evaluación SSVC | CISA-ADP · explotación PoC pública | |
| Divulgación | Modificada | Última actualización del registro | |
| Monitoreo | Detectada | Ingresó al índice |
PraisonAI is a multi-agent teams system. In versions 3.9.26 through 4.6.57 of praiseonai and 0.12.12 through 1.6.57 of praiseonaiagents, the workflow "include" feature is vulnerable to code execution. Workflow._execute_include() implicitly imports and runs an included recipe's tools.py via a raw importlib.util.spec_from_file_location() and spec.loader.exec_module() call, without honoring the PRAISONAI_ALLOW_TEMPLATE_TOOLS/PRAISONAI_ALLOW_LOCAL_TOOLS autoload opt-in gates or routing through the centralized safe loader that protects the other tools.py autoload paths. As a result, a workflow that includes an attacker-controlled local recipe directory executes arbitrary module-level Python code during include setup, before any child workflow parsing or model call, and the same sink is reachable through the higher-level praisonai.recipe.run() recipe API. An attacker who can cause a victim process to run a workflow or recipe that includes an untrusted local recipe achieves arbitrary Python code execution as the PraisonAI process user, a variant that bypasses the hardening applied to the previously disclosed automatic tools.py RCE advisory family. This issue has been fixed in version 4.6.58 of praisonai and 1.6.58 of praisonaiagents.
Desglose de métricas
Rangos afectados
Estado del parche por paquete
| Paquete / producto | Estado | Corregida en | Desde divulgación | Última versión |
|---|---|---|---|---|
pypipraisonaiagents |
Corregida | 1.6.58 | -53 d | 1.7.22 no afectada |
pypipraisonai |
Corregida | 4.6.58 | -53 d | 4.7.26 no afectada |
1.6.584.6.58Arsenal público
Sin exploits, módulos ni PoC públicos conocidos a la fecha de verificación.
https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-hxmv-c4g6-5fqcLas referencias externas se muestran para copiar: cve.llama.ec no lo redirige a otros sitios.
