Use of Externally-Controlled Input to Select Classes or Code ('Unsafe Reflection')

Overview agno is an Agno: a lightweight library for building Multi-Agent Systems Affected versions of this package are vulnerable to Use of Externally-Controlled Input to Select Classes or Code 'Unsafe Reflection' via unsafe reflection in PandasTools, where model-controlled function names are...

CVE-2026-119050

Agno through 3.1.11 contains an unsafe reflection vulnerability in PandasTools that allows attackers to invoke arbitrary pandas functions by supplying model-controlled function names to getattr. Attackers can use prompt injection to make the agent call pandas.readpickle on attacker-controlled pat...

CVE-2026-119050

Agno versions through 3.1.11 are vulnerable to Code Execution due to an unsafe reflection flaw in PandasTools . The vulnerability occurs when the application uses getattr() with model-controlled function names, allowing an attacker to invoke arbitrary pandas functions. Through prompt injection , ...

CVE-2026-119050 Agno through 3.1.11 Code Execution via PandasTools Unsafe Reflection

Agno through 3.1.11 contains an unsafe reflection vulnerability in PandasTools that allows attackers to invoke arbitrary pandas functions by supplying model-controlled function names to getattr. Attackers can use prompt injection to make the agent call pandas.readpickle on attacker-controlled pat...

CVE-2026-119050

Agno through 3.1.11 contains an unsafe reflection vulnerability in PandasTools that allows attackers to invoke arbitrary pandas functions by supplying model-controlled function names to getattr. Attackers can use prompt injection to make the agent call pandas.readpickle on attacker-controlled pat...

EUVD-2026-112816

Agno through 3.1.11 contains an unsafe reflection vulnerability in PandasTools that allows attackers to invoke arbitrary pandas functions by supplying model-controlled function names to getattr. Attackers can use prompt injection to make the agent call pandas.readpickle on attacker-controlled pat...

CVE-2026-119050 Agno through 3.1.11 Code Execution via PandasTools Unsafe Reflection

Agno through 3.1.11 contains an unsafe reflection vulnerability in PandasTools that allows attackers to invoke arbitrary pandas functions by supplying model-controlled function names to getattr. Attackers can use prompt injection to make the agent call pandas.readpickle on attacker-controlled pat...

PT-2026-132124

Name of the Vulnerable Software and Affected Versions Agno versions prior to 3.1.12 Description An unsafe reflection issue exists in PandasTools where model-controlled function names are passed to the getattr function. This allows an attacker to use prompt injection to invoke arbitrary pandas...

Agno code injection vulnerability

Versions 3.1.11 and earlier of Agno contain a code injection vulnerability. This vulnerability stems from an insecure reflection flaw in PandasTools, which allows arbitrary pandas functions to be invoked by providing a function name that controls the model to getattr. Attackers can exploit this b...

CVE-2026-119050: agno-agi agno: Agno through 3.1.11 contains an unsafe reflection vulnerability in PandasTools that allows attackers to invoke…

Agno through 3.1.11 contains an unsafe reflection vulnerability in PandasTools that allows attackers to invoke arbitrary pandas functions by supplying model-controlled function names to getattr. Attackers can use prompt injection to make the agent call pandas.readpickle on attacker-controlled pat...

GHSA-M4W4-3R8H-JW98 Agno: Arbitrary code execution via `eval()` on `field_type` in `FunctionCall`

Impact Agno versions prior to 2.3.24 contain an arbitrary code execution vulnerability in the model execution component. The fieldtype parameter on a FunctionCall input field was passed to Python's built-in eval, allowing an attacker who could influence that value to execute arbitrary Python code...

EUVD-2026-18334

Agno: Arbitrary code execution via eval on fieldtype in FunctionCall...

Agno: Arbitrary code execution via `eval()` on `field_type` in `FunctionCall`

Impact Agno versions prior to 2.3.24 contain an arbitrary code execution vulnerability in the model execution component. The fieldtype parameter on a FunctionCall input field was passed to Python's built-in eval, allowing an attacker who could influence that value to execute arbitrary Python code...

Astra Linux – Vulnerabilities in Linux, Linux-5.10, Linux-5.15, Linux-6.1

In the Linux kernel, the following vulnerability has been resolved: jfs: fixed an array-index-out-of-bounds issue in diAlloc. Currently, there is no check for the agnno of the iag when allocating new inodes to avoid fragmentation problems. The check has been added, which is necessary...

Execution with Unnecessary Privileges

Overview agno is an Agno: a lightweight library for building Multi-Agent Systems Affected versions of this package are vulnerable to Execution with Unnecessary Privileges via the memberagent.run function in libs/agno/agno/team/defaulttools.py, within the Delegation Feature. An authenticated remot...

Improper Control of Dynamically-Managed Code Resources

Overview agno is an Agno: a lightweight library for building Multi-Agent Systems Affected versions of this package are vulnerable to Improper Control of Dynamically-Managed Code Resources via runpythoncode in PythonTools, which executes model-generated Python using exec with full builtins, import...

Command Injection

Overview agno is an Agno: a lightweight library for building Multi-Agent Systems Affected versions of this package are vulnerable to Command Injection via CodingTools.runshell in restricted mode, where an attacker can pass interpreter flags such as -c to allowlisted commands like python3 or pip t...

Arbitrary Code Injection

Overview agno is an Agno: a lightweight library for building Multi-Agent Systems Affected versions of this package are vulnerable to Arbitrary Code Injection via the runpythoncode function in python.py of the PythonTools component, where the code argument is passed without sufficient validation,...

Missing Authentication for Critical Function

Overview agno is an Agno: a lightweight library for building Multi-Agent Systems Affected versions of this package are vulnerable to Missing Authentication for Critical Function via the getauthenticationdependency function in auth.py, where manipulation of the securitykey argument allows an...

CVE-2026-108819

A security flaw has been discovered in agno-agi agno up to 3.0.6/3.1.1. This vulnerability affects the function exec of the component Agent Orchestration Layer. Performing a manipulation of the argument code results in dynamically-managed code resources. Remote exploitation of the attack is...