Skip to content
OpenAdvisories
High · 8.8 CVE-2026-57117 EUVD-2026-108902GHSA-w6h2-fr4q-xvxvPYSEC-2026-3522

PraisonAI: Compute-bridged file tools allow shell command injection

Published Oct 23, 2026 · Updated Oct 30, 2026 · Assigned by GitHub_M

Description

PraisonAI is a multi-agent teams system. From version 4.6.10 to before version 4.6.59, LocalManagedAgent / SandboxedAgent compute bridging wraps read_file, list_files, and write_file when a compute provider is attached. The bridge converts those file operations into shell command strings using raw path arguments, then sends those strings to shell-backed compute providers. An attacker who can influence a file-tool path argument can break out of the quoted path and execute arbitrary shell commands in the compute environment. With compute="local", commands execute through the local subprocess compute provider on the host. With Docker, commands execute in the container. This issue has been patched in version 4.6.59.

Affected products

VendorProductAffectedFixed
MervinPraison PraisonAI >= 4.6.10, < 4.6.59 —

Affected packages

EcosystemPackageAffectedFixedRecord
PyPI praisonai >= 4.6.10, < 4.6.59 4.6.59 GHSA-w6h2-fr4q-xvxv

References