PraisonAI: Compute-bridged file tools allow shell command injection

Overview

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

• PraisonAI >= 4.6.10, < 4.6.59

Remediation

Refer to the linked advisories for vendor-supplied fixes and affected version ranges.

Package advisory (CVE-2026-57117)

Affected packages:

• praisonai >= 4.6.10, < 4.6.59

Patched in:

• praisonai 4.6.59

Source: https://osv.dev/vulnerability/GHSA-w6h2-fr4q-xvxv