Improper Neutralization of Input Used for LLM Prompting Affecting omni-cortex package, versions [,1.4.0)
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-OMNICORTEX-15181366
- published3 Feb 2026
- disclosed1 Feb 2026
- creditUnknown
Introduced: 1 Feb 2026
CVE NOT AVAILABLE CWE-1427 (opens in a new tab)Common Weakness Enumeration (CWE) is a category system for software weaknesses
How to fix?
Upgrade omni-cortex to version 1.4.0 or higher.
Overview
omni-cortex is a Give Claude Code a perfect memory - auto-logs everything, searches smartly, and gets smarter over time
Affected versions of this package are vulnerable to Improper Neutralization of Input Used for LLM Prompting. LLM prompt construction fails to sanitize user-controlled input, leading to attackers being able to manipulate AI model responses and bypass intended system instructions through specially crafted input that alters the prompt context.