dbcve.org
Uncontrolled Resource ConsumptionWeakness · CWE-400

CVE-2026-33235

HIGH · 7.7 CVSS v3.1 Published 2026-06-24
Mitigation only
No fix yet — a mitigation exists. There is no fixed release. A documented workaround reduces exposure in the meantime.
See remediation →
83/100
Remediation priority · High
Remotely reachable Zero-click 8 weeks old

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
AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. In versions prior to 0.6.52, the Fill Text Template block is vulnerable to a Denial of Service (DoS) attack. While the backend implements a SandboxedEnvironment to prevent unauthorized attribute access (e.g., blocking __class__), it fails to limit the computational complexity or execution time of the expressions. An attacker can input computationally expensive Python/Jinja2 expressions that consume the server's CPU and memory, leading to a complete system hang or crash. In multi-tenant or self-hosted environments, this results in a complete service outage and "noisy neighbor" effects that require manual administrative intervention to recover. This issue has been fixed in version 0.6.52.

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 · high confidence

The Fill Text Template block in AutoGPT uses a SandboxedEnvironment to block unauthorized attribute access (e.g., __class__) but fails to impose computational complexity or execution time limits on Jinja2/Python expressions. Attackers can supply computationally expensive expressions that consume excessive CPU and memory, causing server hang, crash, or complete service outage with noisy neighbor effects in multi-tenant environments.

MitigationUpgrade to AutoGPT version 0.6.52 or later, which implements expression complexity limits and execution timeouts in the SandboxedEnvironment.

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
Low
User interaction
None
Scope
Changed
Confidentiality
None
Integrity
None
Availability
High

CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:N/I:N/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. Identify installed AutoGPT version
    Run 'pip show autogpt' or check the package version in your Python environment. Alternatively, check the version file in the AutoGPT installation directory.
    Affected if Version is below 0.6.52 (the version that includes the fix)
  2. Locate Fill Text Template block usage
    Search project source code for references to 'FillTextTemplate' or 'fill_text_template' function calls, and review any workflows or configurations that invoke this block.
    Affected if The Fill Text Template block is actively used in any workflow or automation
  3. Inspect SandboxedEnvironment configuration
    Find the file defining the SandboxedEnvironment class (typically in the template or agents module). Look for timeout, execution_time_limit, or complexity_limit parameters in the environment initialization.
    Affected if The SandboxedEnvironment has no timeout or complexity limit parameters configured, or these parameters are set to None/unrestricted
  4. Check template rendering code for resource limits
    Review the code that executes Jinja2 templates (typically where 'environment.render' or 'template.render' is called). Look for any timeouts, resource quotas, or iteration limits applied to the render operation.
    Affected if No computational limits, timeouts, or complexity checks are applied during template rendering
  5. Review multi-tenant configuration if applicable
    If running in a multi-tenant environment, check whether template execution is isolated per tenant and whether any rate limiting exists on template block usage.
    Affected if No tenant isolation or rate limiting on template block execution is configured

You are affected if AutoGPT version is below 0.6.52 AND the Fill Text Template block is in use, because the SandboxedEnvironment lacks computational complexity or execution time limits on Jinja2 expressions.

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.

dbcve · scoped
Mitigation available No clean upgrade yet — mitigate in the meantime
Mitigation

Upgrade to AutoGPT version 0.6.52 or later, which implements expression complexity limits and execution timeouts in the SandboxedEnvironment.

Recommended fix High confidence

0.6.52 or later

  1. 1. Identify the current AutoGPT installation version (e.g., via package manager, Docker image tag, or application startup logs)
  2. 2. Stop the AutoGPT service to prevent active exploitation during upgrade
  3. 3. Upgrade AutoGPT to version 0.6.52 or later using the appropriate installation method (e.g., pip install autogpt==0.6.52, docker pull autogpt/autogpt:0.6.52, or pulling the latest release from the GitHub repository)
  4. 4. Restart the AutoGPT service
  5. 5. Verify the Fill Text Template block functions correctly with the new version

Generated from the published advisory — verify against the referenced sources before acting.

Have this fixed Scoped from the published advisory
  • Consultation2.0 h
  • Implementation6.0 h
  • Testing4.0 h
  • Review / QA2.0 h
14.0 hours of engineering $2,440
Get help mitigating

An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $3,904.

Scan for this in your stack

Free · runs locally
dbcve dependency scanner

Check whether your project pulls in CVE-2026-33235 — 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-2026-33235 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