CVE-2026-45023
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 · uneditedAutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. Prior to 0.6.59, POST /api/blocks/{block_id}/execute endpoint executes blocks without consuming any credits, regardless of the user's balance. The credit check that exists in the graph execution path (manager.py) is never reached when blocks are called directly via the external API, allowing unlimited free execution of all blocks. This vulnerability is fixed in 0.6.59.
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 confidenceThe /api/blocks/{block_id}/execute endpoint in AutoGPT versions prior to 0.6.59 allows authenticated users to execute blocks without consuming credits, bypassing the credit check that exists in the normal graph execution path (manager.py). This enables unlimited free execution of all blocks via direct API calls.
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
- Unchanged
- Confidentiality
- None
- Integrity
- Low
- Availability
- Low
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/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 checksWork through these to decide whether this CVE applies to you.
-
Determine installed AutoGPT versionRun 'pip show autogpt' or check the version file in your AutoGPT installation directory to identify the current version numberAffected if The installed version is lower than 0.6.59 (e.g., 0.6.58, 0.6.0, etc.)
-
Locate the blocks API endpoint handlerSearch the codebase for the file containing the /api/blocks/{block_id}/execute endpoint definition, typically in an API routes or endpoints directoryAffected if The endpoint handler file exists and lacks credit validation logic before block execution
-
Inspect credit validation in block execution pathExamine the execute function in the blocks endpoint handler to determine whether a credit balance check occurs before processing the block requestAffected if The endpoint executes blocks without calling any credit validation function or checking account balance
-
Compare with graph execution credit checkLocate the credit validation in manager.py (used by the graph execution path) and compare it to the direct block API pathAffected if manager.py contains credit validation logic but the direct /api/blocks/{block_id}/execute path does not perform equivalent checks
-
Verify API exposureConfirm the /api/blocks/{block_id}/execute endpoint is accessible (check API router registration and any middleware that may restrict access)Affected if The endpoint is exposed and reachable without additional authentication or validation layers that would compensate for the missing credit check
You are affected if your AutoGPT version is below 0.6.59 and the direct block execution API endpoint is accessible without performing credit balance validation before execution.
Generated from the published advisory. Verify against your own configuration.
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 · scopedUpgrade to AutoGPT version 0.6.59 or later, which includes the credit check fix for the block execution API endpoint.
0.6.59
- 1. Identify the currently installed AutoGPT version by checking the project's version file or git tags
- 2. Backup the current installation including configuration files and any custom data
- 3. If using pip, run: pip install autogpt==0.6.59
- 4. If using Docker, update the image tag to the version containing 0.6.59
- 5. If using git, run: git fetch origin && git checkout v0.6.59 or git checkout 0.6.59
- 6. Review and apply any new configuration requirements in the upgrade
- 7. Verify the installation: pip show autogpt | grep Version
- 8. Test that the /api/blocks/{block_id}/execute endpoint now properly validates credit balance before execution
Generated from the published advisory — verify against the referenced sources before acting.
- Consultation2.0 h
- Implementation4.0 h
- Testing4.0 h
- Review / QA2.0 h
An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $3,328.
Scan for this in your stack
Free · runs locallyCheck whether your project pulls in CVE-2026-45023 — or any other known-vulnerable package — straight from your lock files. Free and open source; it runs locally and uploads nothing.
References Go to the primary sourcePrimary sources — vendor advisories, patches and trackers. Where our summary and a reference disagree, the reference wins.
Primary sourcesPractitioner notes
ContributedPeer-ranked notes from engineers who’ve handled CVE-2026-45023 in production — separate from our analysis above.
The advisory tells you what broke. It rarely tells you what actually worked. If you’ve dealt with this one, that detail is what the next engineer is searching for.
- The version that genuinely resolved it — not the one the vendor claimed
- A config change or rule that shut the vector down
- A gotcha in the upgrade path that cost you an afternoon
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.
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.
- 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