dbcve.org
LettaApplication

CVE-2026-4965

CRITICAL · 9.8 CVSS v3.1 Published 2026-03-27
Mitigation only
No fix yet — a mitigation exists. There is no fixed release. A documented workaround reduces exposure in the meantime.
See remediation →
100/100
Remediation priority · Urgent
Public exploit 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 was detected in letta-ai letta 0.16.4. This issue affects the function resolve_type of the file letta/functions/ast_parsers.py of the component Incomplete Fix CVE-2025-6101. Performing a manipulation results in improper neutralization of directives in dynamically evaluated code. The attack can be initiated remotely. The exploit is now public and may be used. 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 code injection vulnerability exists in the resolve_type function of letta/functions/ast_parsers.py in letta-ai letta version 0.16.4. This is an incomplete fix for CVE-2025-6101, indicating the previous remediation was insufficient. The vulnerability allows improper neutralization of directives in dynamically evaluated code, enabling remote attackers to inject and execute arbitrary code via specially crafted input.

MitigationDisable or restrict access to the resolve_type function and any dynamic code evaluation paths until an official patch is released; implement strict input validation and sandboxing for any user-controlled data passed to dynamic evaluation functions.

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

Affected products & versions What the vendor confirmedThe version ranges the vendor confirmed as vulnerable. If your version sits inside a range here, treat yourself as exposed until you have upgraded.

NVD · CPE data
LettaApplication
Affected:= 0.16.4

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
High
Integrity
High
Availability
High

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

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. Check installed Letta version
    Run 'pip show letta-ai' or 'pip list | grep letta' to identify the installed version of the letta package
    Affected if Version is 0.16.4 exactly
  2. Locate vulnerable ast_parsers.py file
    Find the file 'letta/functions/ast_parsers.py' in your Letta installation directory (typically in site-packages or your projectvenv/lib/python*/site-packages/letta/)
    Affected if File exists and is from letta version 0.16.4
  3. Inspect resolve_type function for dynamic evaluation
    Open ast_parsers.py and locate the resolve_type function; search for use of eval(), exec(), or similar dynamic code execution within this function
    Affected if Function contains dynamic evaluation (eval/exec calls) that processes untrusted input
  4. Determine if AST parsing is actively used
    Check if your Letta deployment uses function parsing or AST-based code processing - review application logs or configuration for calls to functions that invoke ast_parsers
    Affected if AST parsing functionality is enabled and processing external inputs
  5. Check for external input sources to resolve_type
    Audit your application to identify if user-controlled data, API inputs, or external data sources can reach the resolve_type function in ast_parsers.py
    Affected if Untrusted input can reach the resolve_type function without sanitization

You are affected if you are running Letta version 0.16.4 AND the resolve_type function with dynamic evaluation is exposed to external or untrusted input through your application.

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

Disable or restrict access to the resolve_type function and any dynamic code evaluation paths until an official patch is released; implement strict input validation and sandboxing for any user-controlled data passed to dynamic evaluation functions.

Fix this in Letta Scoped from the published advisory
  • Consultation4.0 h
  • Implementation8.0 h
  • Testing6.0 h
  • Review / QA4.0 h
22.0 hours of engineering $3,860
Get help mitigating

An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $6,176.

Scan for this in your stack

Free · runs locally
dbcve dependency scanner

Check whether your project pulls in CVE-2026-4965 — 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-2026-4965 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