CVE-2026-57120

PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.59, executecode sandbox mode permits runtime assembly of blocklisted dunder names and allows str.format or str.formatmap to resolve dotted fields through C-level attribute access that bypasses safegetattr. This exposes class,...

CVE-2026-57120: Protection Mechanism Failure

PraisonAI is a multi-agent teams system. Prior to praisonaiagents 1.6.59, executecode sandbox mode permits runtime assembly of blocklisted dunder names and allows str.format or str.formatmap to resolve dotted fields through C-level attribute access that bypasses safegetattr. This exposes class,...

CVE-2026-47392

PraisonAI is a multi-agent teams system. Prior to version 4.6.40 of PraisonAI, corresponding to version 1.6.40 of praisonaiagents, "executecode" in "praisonaiagents/tools/pythontools.py" v1.6.37, subprocess sandbox mode can be fully bypassed using "print.self" to retrieve the real Python "builtin...

CVE-2026-47392: Incomplete List of Disallowed Inputs

PraisonAI is a multi-agent teams system. Prior to version 4.6.40 of PraisonAI, corresponding to version 1.6.40 of praisonaiagents, executecode in praisonaiagents/tools/pythontools.py v1.6.37, subprocess sandbox mode can be fully bypassed using print.self to retrieve the real Python builtins modul...

PraisonAI: Python Sandbox Escape via str Subclass startswith() Override in execute_code

Summaryexecutecode in praisonai-agents runs attacker-controlled Python inside a three-layer sandbox that can be fully bypassed by passing a str subclass with an overridden startswith method to the safegetattr wrapper, achieving arbitrary OS command execution on the host. Detailspythontools.py:20...

PraisonAI has an unspecified vulnerability

PraisonAI is a low-code multi-intelligent body collaboration framework. PraisonAI suffers from a security vulnerability that stems from the fact that the three-layer sandboxing of the executecode function can be completely bypassed, which can be exploited by an attacker to cause the execution of...

CVE-2026-39888

PraisonAI is a multi-agent teams system. Prior to 1.5.115, executecode in praisonaiagents.tools.pythontools defaults to sandboxmode="sandbox", which runs user code in a subprocess wrapped with a restricted builtins dict and an AST-based blocklist. The AST blocklist embedded inside the subprocess...

CVE-2026-39888 PraisonAIAgents has a sandbox escape via exception frame traversal in `execute_code` (subprocess mode)

PraisonAI is a multi-agent teams system. Prior to 1.5.115, executecode in praisonaiagents.tools.pythontools defaults to sandboxmode="sandbox", which runs user code in a subprocess wrapped with a restricted builtins dict and an AST-based blocklist. The AST blocklist embedded inside the subprocess...

Arbitrary Code Injection

Overview praisonaiagents is a Praison AI agents for completing complex tasks with Self Reflection Agents Affected versions of this package are vulnerable to Arbitrary Code Injection via the executecode function. An attacker can gain unauthorized access to the host environment, execute arbitrary...

EUVD-2026-20635

PraisonAI has sandbox escape via exception frame traversal in executecode subprocess mode...

CVE-2026-39888: Violation of Secure Design Principles

PraisonAI is a multi-agent teams system. Prior to 1.5.115, executecode in praisonaiagents.tools.pythontools defaults to sandboxmode="sandbox", which runs user code in a subprocess wrapped with a restricted builtins dict and an AST-based blocklist. The AST blocklist embedded inside the subprocess...

CVE-2026-34371 LibreChat Affected by Arbitrary File Write via `execute_code` Artifact Filename Traversal

LibreChat is a ChatGPT clone with additional features. Prior to 0.8.4, LibreChat trusts the name field returned by the executecode sandbox when persisting code-generated artifacts. On deployments using the default local file strategy, a malicious artifact filename containing traversal sequences f...

CVE-2026-34371 LibreChat Affected by Arbitrary File Write via `execute_code` Artifact Filename Traversal

LibreChat is a ChatGPT clone with additional features. Prior to 0.8.4, LibreChat trusts the name field returned by the executecode sandbox when persisting code-generated artifacts. On deployments using the default local file strategy, a malicious artifact filename containing traversal sequences f...

CVE-2026-34371: Improper Limitation of a Pathname to a Restricted Directory

LibreChat is a ChatGPT clone with additional features. Prior to 0.8.4, LibreChat trusts the name field returned by the executecode sandbox when persisting code-generated artifacts. On deployments using the default local file strategy, a malicious artifact filename containing traversal sequences f...

CVE-2026-34938

PraisonAI is a multi-agent teams system. Prior to version 1.5.90, executecode in praisonai-agents runs attacker-controlled Python inside a three-layer sandbox that can be fully bypassed by passing a str subclass with an overridden startswith method to the safegetattr wrapper, achieving arbitrary ...

EUVD-2026-18919

PraisonAI is a multi-agent teams system. Prior to version 1.5.90, executecode in praisonai-agents runs attacker-controlled Python inside a three-layer sandbox that can be fully bypassed by passing a str subclass with an overridden startswith method to the safegetattr wrapper, achieving arbitrary ...

CVE-2026-34938: Protection Mechanism Failure

PraisonAI is a multi-agent teams system. Prior to version 1.5.90, executecode in praisonai-agents runs attacker-controlled Python inside a three-layer sandbox that can be fully bypassed by passing a str subclass with an overridden startswith method to the safegetattr wrapper, achieving arbitrary ...

Arbitrary Code Injection

Overview praisonaiagents is a Praison AI agents for completing complex tasks with Self Reflection Agents Affected versions of this package are vulnerable to Arbitrary Code Injection via the executecode method. An attacker can execute arbitrary operating system commands by passing a crafted str...

CVE-2024-4326 Remote Code Execution via `/apply_settings` and `/execute_code` in parisneo/lollms-webui

A vulnerability in parisneo/lollms-webui versions up to 9.3 allows remote attackers to execute arbitrary code. The vulnerability stems from insufficient protection of the /applysettings and /executecode endpoints. Attackers can bypass protections by setting the host to localhost, enabling code...

CVE-2024-4326

A vulnerability in parisneo/lollms-webui versions up to 9.3 allows remote attackers to execute arbitrary code. The vulnerability stems from insufficient protection of the "/applysettings" and "/executecode" endpoints. Attackers can bypass protections by setting the host to localhost, enabling cod...