Vulnerability · Published Aug 14, 2026 · Assigned by GitHub_M
CVE-2026-49986Cortex has Untrusted Project Bootstrap Code Execution via `CLAUDE_PROJECT_DIR`
High 7.1
In plain English
A high-severity security flaw in Cortex from cdeust. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.2% (higher than 5% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.
Official description
The Cortex MCP server (`neuro-cortex-memory`), a cross-platform persistent memory MCP, prior to version 3.17.1 treats the `CLAUDE_PROJECT_DIR` environment variable — automatically set by Claude Code to the currently open project directory — as a trusted Cortex developer checkout. When the `open_visualization` tool is invoked, `_find_dev_source()` resolves the user's active project directory as a candidate Cortex source root. The only validation performed by `_is_cortex_root()` is a check for the presence of an `mcp_server/` subdirectory and a `ui/unified-viz.html` file. An attacker who places these two marker files in a malicious repository can cause Cortex to execute an arbitrary `mcp_server/server/visualize_bootstrap.py` from that directory via `subprocess.run([sys.executable, ...])`, achieving code execution with the privileges of the victim's local user process. Version 3.17.1 fixes the issue.
Affected packages & fixed versions
| Ecosystem | Package | Fixed in | Advisory |
|---|---|---|---|
| PyPI | neuro-cortex-memory | 3.18.0 | GHSA-gvpp-v77h-5w8g |
| PyPI | neuro-cortex-memory | 3.18.0 | PYSEC-2026-2676 |
Affected products (as reported)
Weakness: CWE-829 · Vector: CVSS:4.0/AV:L/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:P