AutoGPT is a workflow automation platform for creating, deploying, and managing continuous artificial intelligence agents
AutoGPT versions 0.6.34-0.6.51 are vulnerable because they deserialize Redis cache data using Python's `pickle.loads` without proper security checks. If an attacker can inject malicious data into the Redis cache, the backend will execute arbitrary code during deserialization.
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.
Organizations using affected AutoGPT versions are at high risk of arbitrary code execution, potentially leading to full system compromise, if an attacker can poison their Redis cache.
Remediation Recommended
This vulnerability carries significant risk. Schedule patching in your next cycle.
What should I do?
Published
CVE disclosed publicly
Last Modified
Most recent update
Indexed to CVEInsight
Added to this platform
AV:A/AC:H/PR:H/UI:N/S:C/C:H/I:H/A:H
0
Affected Products
2
References
CVSS:3.1/AV:A/AC:H/PR:H/UI:N/S:C/C:H/I:H/A:H
Exploitability
Impact