Improper Control of Dynamically-Managed Code Resources Affecting agno package, versions [0,]
Threat Intelligence
Snyk has a proof-of-concept or detailed explanation of how to exploit this vulnerability.
The probability is the direct output of the EPSS model, and conveys an overall sense of the threat of exploitation in the wild. The percentile measures the EPSS probability relative to all known EPSS scores. Note: This data is updated daily, relying on the latest available EPSS model version. Check out the EPSS documentation for more details.
Do your applications use this vulnerable package?
In a few clicks we can analyze your entire application and see what components are vulnerable in your application, and suggest you quick fixes.
Test your applications- Snyk IDSNYK-PYTHON-AGNO-20877467
- published13 Oct 2026
- disclosed12 Oct 2026
- creditYbyu
Introduced: 12 Oct 2026
NewCVE-2026-108819 (opens in a new tab)How to fix?
There is no fixed version for agno.
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 run_python_code in PythonTools, which executes model-generated Python using exec() with full builtins, imports, filesystem, and network access. Despite their names, safe_globals and safe_locals impose no security boundary - they merely seed the execution namespace and do not restrict what the executed code can import or access. Similarly, restrict_to_base_dir constrains only file-path arguments to the file helpers and does nothing to prevent executed code from reading arbitrary files such as /etc/passwd, dumping os.environ, or making network connections. An attacker who can influence the model's input (for example via prompt injection) can achieve arbitrary code execution in the host process.