dbcve.org
Code InjectionWeakness · CWE-94

CVE-2026-33233

HIGH · 7.6 CVSS v3.1 Published 2026-05-19
Mitigation only
No fix yet — a mitigation exists. There is no fixed release. A documented workaround reduces exposure in the meantime.
See remediation →
78/100
Remediation priority · High
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
AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents. In versions 0.6.34 through 0.6.51, the backend deserializes Redis cache bytes using pickle.loads without integrity/authenticity checks. The write path serializes values with pickle.dumps(...) into Redis and the read path blindly invokes pickle.loads(...) on bytes with no HMAC/signature or strict schema validation gating deserialization. If an attacker can poison a shared-cache key in Redis, arbitrary command execution is possible in the backend container context, affecting confidentiality, integrity, and availability. 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

AutoGPT versions 0.6.34-0.6.51 use pickle.loads() to deserialize data from Redis cache without any integrity verification. Since pickle can execute arbitrary code during deserialization, an attacker with access to poison a shared Redis cache key can achieve remote code execution on the backend.

MitigationUpgrade to version 0.6.52 or later. Additionally, replace pickle with safe serialization (JSON/MessagePack) or implement HMAC-signed validation before deserialization to prevent cache poisoning attacks.

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
Adjacent
Complexity
High
Privileges
High
User interaction
None
Scope
Changed
Confidentiality
High
Integrity
High
Availability
High

CVSS:3.1/AV:A/AC:H/PR:H/UI:N/S:C/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 AutoGPT version
    Run 'pip show autogpt' or check the version file in your AutoGPT installation directory. Compare the version number against the affected range 0.6.34 to 0.6.51.
    Affected if Version falls within 0.6.34 through 0.6.51 inclusive
  2. Verify Redis cache is enabled
    Check your AutoGPT configuration files (such as config.py, .env, or settings.json) for Redis connection settings. Look for REDIS_HOST, REDIS_PORT, or CACHE_BACKEND=redis settings.
    Affected if Redis is configured as the cache backend
  3. Inspect cache serialization code
    Locate the cache implementation files in your AutoGPT installation. Search for 'pickle.loads' or 'pickle.dumps' calls within cache-related modules (typically in a 'cache' or 'storage' directory).
    Affected if Code contains pickle.loads() for deserializing cached data
  4. Check for cache integrity validation
    Search the cache code for HMAC, signature, or hash verification before deserialization. Look for terms like 'verify', 'hmac', 'signature', or 'integrity' in the cache read path.
    Affected if No HMAC, signature, or hash validation exists before calling pickle.loads()
  5. Confirm pickle is used for cache storage
    Examine the cache write path to verify pickle.dumps() is being used to serialize data before storing in Redis.
    Affected if Cache write operations use pickle.dumps() without any integrity mechanism

You are affected if AutoGPT version is between 0.6.34 and 0.6.51, Redis cache is enabled, and the cache deserialization relies on pickle.loads() without any integrity verification like HMAC signatures.

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 version 0.6.52 or later. Additionally, replace pickle with safe serialization (JSON/MessagePack) or implement HMAC-signed validation before deserialization to prevent cache poisoning attacks.

Recommended fix High confidence

0.6.52

  1. Upgrade AutoGPT from any version between 0.6.34 and 0.6.51 to version 0.6.52 or later
  2. Verify the upgrade by checking the installed version with the package manager or application version command
  3. After upgrading, confirm that Redis cache operations no longer use unsafe pickle.loads/pickle.dumps and instead use safer deserialization methods with integrity checks

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

Have this fixed Scoped from the published advisory
  • Consultation3.0 h
  • Implementation8.0 h
  • Testing6.0 h
  • Review / QA3.0 h
20.0 hours of engineering $3,480
Get help mitigating

An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $5,568.

Scan for this in your stack

Free · runs locally
dbcve dependency scanner

Check whether your project pulls in CVE-2026-33233 — 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-2026-33233 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