AutoGPT Platform: Remote Code Execution via Unsafe Pickle Deserialization of Redis Cache Entries
Key facts
- Attack vector
- Adjacent network
- Privileges required
- High
- User interaction
- None
- Attack complexity
- High
- Impact type
- Security bypass, Code execution
- Confidentiality · integrity · availability
- High · High · High
- Fix status
- Fixed
Attack profile from CVSS 3.1 · CNA. Fix status from CNA. Impact type from CWE-345 and CWE-502.
Summary
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.
Why it matters now
SSVC decision points
CISA ADP · SSVC 2.0.3
- Exploitation
- Poc
- Automatable
- No
- Technical impact
- Total
The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.
Affected products
| Vendor | Product | Affected versions | Fixed in | Status | Source |
|---|---|---|---|---|---|
| Significant-Gravitas | AutoGPT | 0.6.34 to before 0.6.52 | 0.6.52 | Patch available | CNA |
- AutoGPT VendorSignificant-Gravitas Affected 0.6.34 to before 0.6.52 Fixed in 0.6.52 Patch available CNA
CPE names Threatist (inferred) · 1
Inferred from how NVD named this product before; not given by a source.
| CPE | Versions | Role | Vendor |
|---|---|---|---|
| cpe:2.3:a:agpt:autogpt_platform:*:*:*:*:*:*:*:* | — | — | Significant-Gravitas |
- cpe:2.3:a:agpt:autogpt_platform:*:*:*:*:*:*:*:* Versions — — ·Significant-Gravitas
Remediation
- Fix · CNA AutoGPT (Significant-Gravitas) Fixed in 0.6.52
Timeline
- 2026-10-02 Threatist record created from CVE-2026-33233
References
More Significant-Gravitas vulnerabilities
- TI-2024-05646 Shell Command Denylist Bypass in significant-gravitas/autogpt CVSS 3.1CRITICAL 9.8
- TI-2026-19981 AutoGPT is Vulnerable to RCE via Disabled Block Execution CVSS 4.0HIGH 8.6
- TI-2025-23508 AutoGPT has a DoS vulnerability in MediaDurationBlock CVSS 4.0HIGH 8.7
- TI-2025-23495 AutoGPT has a DoS vulnerability in ScreenshotWebPageBlock CVSS 4.0HIGH 8.7
- TI-2025-23493 AutoGPT has a DoS vulnerability in FileStoreBlock with StepThroughItemsBlock CVSS 4.0HIGH 8.7
- TI-2025-23471 AutoGPT has a DoS vulnerability in ReadRSSFeedBlock CVSS 4.0HIGH 8.7
Sources
This product uses the NVD API but is not endorsed or certified by the NVD. Sources and licences