CVE-2026-77604vitali87 code-graph-rag path traversal
CVE-2026-77604 is a path traversal in vitali87 code-graph-rag, rated high (7.5 on CVSS 3.1).
Why this priority: A public proof of concept exists and exploitation can be automated.
Published · Updated · NVD status: Received
What it is
A file name from the request can climb out of the intended folder with sequences like ../, reaching files the service never meant to expose.
How it is reached
An attacker can exploit it over the network, without an account, and nobody has to click anything.
What an attacker gains
A successful attack can read the data it protects. In practice, this kind of flaw lets an attacker read or write files outside the folders the service meant to expose.
Is it being exploited?
CISA's SSVC assessment notes a public proof of concept. It can be exploited automatically, at scale.
What to do
- Upgrade vitali87 code-graph-rag to 0.0.345 or later.
- Until it is patched, keep it off the internet or behind a VPN, allowlist or authenticating proxy.
Description from NVD
Code Graph RAG is an AI-powered knowledge graph and retrieval system for querying, understanding, and editing multi-language codebases. Prior to 0.0.345, the MCPToolsRegistry.read_file implementation in codebase_rag/mcp/tools.py joins attacker-controlled file_path input to project_root without resolving and verifying containment when offset or limit selects the paginated branch. An absolute path causes pathlib to discard the configured root, while relative traversal can also resolve outside it. The protected non-paginated branch uses validate_project_path, but the paginated branch bypasses that validation before opening the path. An unauthenticated caller of a network-exposed HTTP MCP server can therefore read arbitrary UTF-8-readable files available to the server process, including credentials, environment data, private keys, source, and configuration; local callers through the stdio transport can reach the same vulnerable code path. This issue is fixed in version 0.0.345.
What this means for your architecture.
A CVE names a product. Whether it matters depends on where that product sits in your systems: what reaches it, which trust boundary it guards and what it can reach once compromised. Veriom maps your components, their relationships and your trust boundaries from your code, cloud and delivery evidence, so you can see where a component like this sits. The radar itself does not look at your systems.
Components it touches
- File storage the service can read or write. The flaw sits between the application and the file system it can reach.
Trust boundaries in play
- Internet-facing entry points. No account is needed. Any instance reachable from outside your perimeter, through a load balancer, gateway, VPN or exposed admin port, is in scope.
- Between the application and the file system it can reach. An attacker who crosses it can read or write files outside the folders the service meant to expose.
Questions to answer about your own systems
- Where does vitali87 code-graph-rag run in your systems, and at which version?
- Which of those instances can be reached from the internet or partner networks?
- What can it reach once compromised: which data stores, secrets and services?
Read more
Patches and commits
Advisories
Sources
- CVE records and CVSS scores from the NVD CVE API. This product uses the NVD API but is not endorsed or certified by the NVD.
- Exploitation status from CISA’s Known Exploited Vulnerabilities catalog.
- Exploit likelihood from FIRST’s Exploit Prediction Scoring System (EPSS), refreshed daily.
- Explanations are written by Veriom from fixed templates over each record’s data, not by a person reviewing each CVE. Descriptions are quoted from the records as published.