CVE-2026-123675

A flaw has been found in OpenBMB Internet of Agents up to 9d78e88e47160eb42ee1ee8538c05e1c2c47877a. This affects the function executecode of the file imclient/agents/tools/codeexecutor.py of the component Code Executor Tool. This manipulation of the argument filename/lang causes code injection. T...

CVE-2026-123675 OpenBMB Internet of Agents Code Executor Tool code_executor.py execute_code code injection

A flaw has been found in OpenBMB Internet of Agents up to 9d78e88e47160eb42ee1ee8538c05e1c2c47877a. This affects the function executecode of the file imclient/agents/tools/codeexecutor.py of the component Code Executor Tool. This manipulation of the argument filename/lang causes code injection. T...

EUVD-2026-118307

A flaw has been found in OpenBMB Internet of Agents up to 9d78e88e47160eb42ee1ee8538c05e1c2c47877a. This affects the function executecode of the file imclient/agents/tools/codeexecutor.py of the component Code Executor Tool. This manipulation of the argument filename/lang causes code injection. T...

CVE-2026-123675

A code injection vulnerability exists in the Code Executor Tool of OpenBMB Internet of Agents (up to commit 9d78e88e47160eb42ee1ee8538c05e1c2c47877a). The flaw is located in the execute_code function within im_client/agents/tools/code_executor.py, where improper handling of the filename/lang argu...

CVE-2026-123675 OpenBMB Internet of Agents Code Executor Tool code_executor.py execute_code code injection

A flaw has been found in OpenBMB Internet of Agents up to 9d78e88e47160eb42ee1ee8538c05e1c2c47877a. This affects the function executecode of the file imclient/agents/tools/codeexecutor.py of the component Code Executor Tool. This manipulation of the argument filename/lang causes code injection. T...

CVE-2026-123675: OpenBMB Internet of Agents: A flaw has been found in OpenBMB Internet of Agents up to 9d78e88e47160eb42ee1ee8538c05e1c2c47877a

A flaw has been found in OpenBMB Internet of Agents up to 9d78e88e47160eb42ee1ee8538c05e1c2c47877a. This affects the function executecode of the file imclient/agents/tools/codeexecutor.py of the component Code Executor Tool. This manipulation of the argument filename/lang causes code injection. T...

CVE-2026-123018

A flaw was found in DB-GPT. A remote attacker could exploit this vulnerability by submitting manipulated input to the executecode function within the CodeAction component. This flaw allows the attacker to execute arbitrary code on the underlying host system, potentially compromising the host...

CVE-2026-123018

A security flaw has been discovered in eosphoros-ai DB-GPT up to 0.8.2. This issue affects the function executecode of the file codeutils.py of the component CodeAction. Performing a manipulation results in code injection. The attack can be initiated remotely. The exploit has been released to the...

EUVD-2026-117405

A security flaw has been discovered in eosphoros-ai DB-GPT up to 0.8.2. This issue affects the function executecode of the file codeutils.py of the component CodeAction. Performing a manipulation results in code injection. The attack can be initiated remotely. The exploit has been released to the...

CVE-2026-123018 eosphoros-ai DB-GPT CodeAction code_utils.py execute_code code injection

A security flaw has been discovered in eosphoros-ai DB-GPT up to 0.8.2. This issue affects the function executecode of the file codeutils.py of the component CodeAction. Performing a manipulation results in code injection. The attack can be initiated remotely. The exploit has been released to the...

CVE-2026-123018

A security flaw exists in eosphoros-ai DB-GPT versions up to 0.8.2 . The vulnerability is located in the CodeAction component, specifically within the execute_code function of the code_utils.py file. A remote attacker can perform a manipulation leading to code injection . An exploit has been rele...

CVE-2026-123018 eosphoros-ai DB-GPT CodeAction code_utils.py execute_code code injection

A security flaw has been discovered in eosphoros-ai DB-GPT up to 0.8.2. This issue affects the function executecode of the file codeutils.py of the component CodeAction. Performing a manipulation results in code injection. The attack can be initiated remotely. The exploit has been released to the...

Eosphoros DB-GPT input validation error vulnerability

Versions 0.8.0, 0.8.1, and 0.8.2 of eosphoros DB-GPT contain a security vulnerability. This vulnerability stems from the executecode function within the file codeutils.py in the CodeAction component, which may lead to code injection. Attackers can exploit this vulnerability remotely...

PraisonAI: Human-in-the-loop tool approval is cached by tool name and silently reused for all subsequent calls with arbitrary arguments

SummaryPraisonAI gates dangerous tools file writes, deletes, shell/code execution behind an interactive approval prompt. The first approval of a tool is cached for the remainder of the run and silently reused for all later invocations of that tool with arbitrary, unreviewed arguments. Root...

CVE-2026-53710: Improper Control of Generation of Code

MCP Context Forge is an AI gateway, registry, and proxy for MCP, A2A, REST, and gRPC APIs. Prior to 1.0.2, the pythonsandboxserver in mcp-servers/python/pythonsandboxserver/src/pythonsandboxserver/serverfastmcp.py exposes raw getattr through safebuiltins, omits a required getattr guard, and relie...

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 PraisonAI: execute_code sandbox bypass: str.format C-level attribute access reads every blocklisted dunder

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

PraisonAI's praisonaiagents package (prior to 1.6.59 ) has a sandbox bypass in the execute_code tool. The subprocess sandbox's AST validator and _safe_getattr wrapper are defeated by combining runtime string assembly of blocklisted dunder names (e.g. "_"*2 + "class" + "_"*2) with C-level attribut...

CVE-2026-57120 PraisonAI: execute_code sandbox bypass: str.format C-level attribute access reads every blocklisted dunder

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 PraisonAI: execute_code sandbox bypass: str.format C-level attribute access reads every blocklisted dunder

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,...