dbcve.org
InjectionWeakness · CWE-74

CVE-2026-5002

HIGH · 7.3 CVSS v3.1 Published 2026-03-28
Mitigation only
No fix yet — a mitigation exists. There is no fixed release. A documented workaround reduces exposure in the meantime.
See remediation →
82/100
Remediation priority · High
Remotely reachable No privileges Zero-click

Official description Straight from the sourceThe vendor's or NVD's own wording, published unedited. Authoritative, but often terse — it says what broke, rarely what to do.

NVD · unedited
A vulnerability has been found in PromtEngineer localGPT up to 4d41c7d1713b16b216d8e062e51a5dd88b20b054. The impacted element is the function _route_using_overviews of the file backend/server.py of the component LLM Prompt Handler. Such manipulation leads to injection. The attack may be performed from remote. The exploit has been disclosed to the public and may be used. This product utilizes a rolling release system for continuous delivery, and as such, version information for affected or updated releases is not disclosed. The vendor was contacted early about this disclosure but did not respond in any way.

Technical summary Written by usOur analysis, written from the advisory, the CVSS vector and the affected-version data. It adds context the advisory leaves out, and never invents facts that are not in the source.

dbcve analysis · moderate confidence

A prompt injection vulnerability exists in the _route_using_overviews function within backend/server.py of localGPT. This LLM Prompt Handler component fails to properly sanitize or validate prompts before processing, allowing remote attackers to inject malicious instructions that could manipulate the LLM's behavior, potentially leading to unauthorized actions or data exposure.

MitigationImplement strict input validation and sanitization for all prompts handled by _route_using_overviews, using context isolation techniques and allowlist-based validation where possible. Additionally, consider implementing prompt detection/filtering layers and ensuring the routing logic cannot be influenced by user-supplied prompt content.

Verify against the referenced sources before acting — the references below are authoritative for this CVE, this summary is not.

CVSS breakdown How the score is builtThe industry scoring standard. It rates how the flaw is reached, what it takes to exploit, and what an attacker gains — the score is derived from those, not the other way round.

From the vector
Attack vector
Network
Complexity
Low
Privileges
None
User interaction
None
Scope
Unchanged
Confidentiality
Low
Integrity
Low
Availability
Low

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:L

Am I affected? How to checkSteps we derive from the advisory and the affected-version data, so you can decide whether this CVE reaches your setup. They are a guide, not a scan — your own configuration is the authority.

dbcve checks

Work through these to decide whether this CVE applies to you.

  1. Locate localGPT installation and identify version
    Search for the localGPT project directory and check for version information in setup files, pyproject.toml, or version.py. If installed via pip, run: pip show localgpt or pip list | grep -i localgpt
    Affected if The installed version matches or precedes any known fixed version, or version information cannot be determined (indicating an unpatched build)
  2. Find the vulnerable file backend/server.py
    Locate backend/server.py within the localGPT project structure. Search for the file path: find . -name 'server.py' -path '*/backend/*'
    Affected if The file exists and contains the _route_using_overviews function, indicating the vulnerable code is present
  3. Inspect the _route_using_overviews function for input validation
    Open backend/server.py and examine the _route_using_overviews function. Look for any input sanitization, validation, or prompt filtering logic before the prompt is processed by the LLM
    Affected if The function processes prompts directly without sanitization, validation, or filtering of user-supplied input
  4. Verify if the routing logic accepts user prompts
    Trace how prompts flow into _route_using_overviews. Check if API endpoints, routes, or input handlers pass user-provided prompts directly to this function without preprocessing
    Affected if User-supplied prompts can reach _route_using_overviews without any cleaning or validation step
  5. Confirm the overviews routing feature is active
    Identify whether the overviews routing feature is enabled in the localGPT configuration or is active by default when processing prompts. Check config files or runtime settings that control this behavior
    Affected if The overviews routing feature is enabled and processes prompts through the vulnerable function

You are affected if localGPT is installed with the _route_using_overviews function present in backend/server.py and user prompts can reach this function without sanitization or validation.

Generated from the published advisory. Verify against your own configuration.

Check your environment

Paste your version and any relevant configuration and it will be compared against the affected criteria above. Do not include secrets or credentials.

AI-assisted, checked against the advisory. Informational, not a guarantee.

Remediation Closing itWhat it takes to close this. Where a vendor fix exists we point at it; where none exists we say so plainly, and can build one. Effort estimates are scoped from the advisory, not from your codebase.

From vendor data
Mitigation available No clean upgrade yet — mitigate in the meantime
Mitigation

Implement strict input validation and sanitization for all prompts handled by _route_using_overviews, using context isolation techniques and allowlist-based validation where possible. Additionally, consider implementing prompt detection/filtering layers and ensuring the routing logic cannot be influenced by user-supplied prompt content.

Have this fixed Scoped from the published advisory
  • Consultation3.0 h
  • Implementation6.0 h
  • Testing3.0 h
  • Review / QA2.0 h
14.0 hours of engineering $2,490
Get help mitigating

An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $3,984.

Scan for this in your stack

Free · runs locally
dbcve dependency scanner

Check whether your project pulls in CVE-2026-5002 — or any other known-vulnerable package — straight from your lock files. Free and open source; it runs locally and uploads nothing.

Get it on GitHub Scan in the browser

References Go to the primary sourcePrimary sources — vendor advisories, patches and trackers. Where our summary and a reference disagree, the reference wins.

Primary sources

Practitioner notes

Contributed

Peer-ranked notes from engineers who’ve handled CVE-2026-5002 in production — separate from our analysis above.

No notes yet

Be the first to add a field note for this CVE — a mitigation you’ve verified, a version caveat, or a link to a working fix. Sign in above to contribute.

What this is

A place for practitioners to share what actually worked: a mitigation you’ve tested, a configuration change, a version- or environment-specific caveat, or a link to a verified patch. The most useful notes rise to the top as peers upvote them, so the signal stays high.

What belongs here
  • Verified mitigations, workarounds, and config changes
  • Version or environment caveats, and links to real fixes
  • No weaponised exploit code, or anything meant to cause harm
  • No spam, self-promotion, credentials, or personal data