Security readout for executives and security teams
Plain-English summary
CVE-2023-37273 is a Docker escape risk in Auto-GPT before 0.4.3. The main exposure is users running Auto-GPT from a cloned repository with the repo-root Docker Compose setup. Malicious custom Python run inside Auto-GPT could alter the Compose configuration and affect the host when Auto-GPT is later restarted.
Executive priority
Prioritize remediation where Auto-GPT is used on developer workstations, automation hosts, or CI systems. Business urgency is high for teams experimenting with autonomous agents because host compromise could follow from a seemingly contained container workflow.
Technical view
The repo-root docker-compose.yml mounted itself into the container without write protection. If Auto-GPT executed malicious custom Python through its Python execution features, that code could overwrite the Compose file and influence the host on the next startup. The issue is fixed in Auto-GPT 0.4.3. CVSS is 8.1, with changed scope and high confidentiality and integrity impact.
Likely exposure
Likely exposure is limited to Auto-GPT versions before 0.4.3 run from a cloned Git repository using the repo-root Docker Compose workflow. Hosted services or installations not using that Compose file are not established as affected by the provided sources.
Exploitation context
The provided sources do not show active exploitation, and the CVE is not listed as KEV. Exploitation requires some prior ability to get malicious custom Python executed by Auto-GPT and user interaction through a later restart.
Researcher notes
This is not a remote unauthenticated service bug based on the supplied evidence. The important validation points are version, launch path, Compose file provenance, and whether Auto-GPT’s Python execution features were exposed to untrusted inputs or agent actions.
Mitigation direction
- Upgrade Auto-GPT to version 0.4.3 or later.
- Stop using affected pre-0.4.3 repo-root Docker Compose setups.
- Review vendor advisory and pull request guidance before restarting older deployments.
- Rebuild containers from trusted source after upgrading.
- Treat altered Compose files in affected checkouts as suspicious.
Validation and detection
- Inventory Auto-GPT deployments and record installed versions.
- Identify instances launched from cloned repositories using repo-root Compose files.
- Review Compose files for unexpected changes before restarting Auto-GPT.
- Confirm affected systems have moved to Auto-GPT 0.4.3 or later.
- Check whether untrusted custom Python was enabled or executed.
Public sources used
Generated from the cited source records. This long-tail analysis has not been individually reviewed by a named human.
Conservative CVE-to-ATT&CK context
These mappings and lookup hints may be relevant to the vulnerability behavior, CWE, affected product, or exposure path. Glexia-inferred context is not an official MITRE, ATT&CK, CWE, or CVE Program mapping.
ATT&CK lookup starting points
Use these exact CWE pages and searches to review the Glexia ATT&CK library from this CVE's weakness and description context.
CWE-94: Code execution behavior lookup
Code execution and unsafe deserialization weaknesses often justify reviewing execution behavior and process telemetry. Open the exact CWE lookup page first, then review the ATT&CK searches from that MITRE weakness context. This is a Glexia lookup hint, not an official ATT&CK mapping.
Open ATT&CK lookupContainer behavior lookup
The affected technology mentions containers, so container-specific ATT&CK technique review may help. This is a Glexia inferred lookup path, not an official MITRE, ATT&CK, or CVE Program mapping.
Open ATT&CK lookupCVE-2023-37273 mapping review
Open the CVE-to-ATT&CK bridge for reviewed, inferred, or future official mappings tied to this CVE.
Open ATT&CK lookup- Severity
- High
- CVSS
- 8.1 (3.1)
- Known Exploited
- No
- Published
Vector: CVSS:3.1/AV:L/AC:L/PR:L/UI:R/S:C/C:H/I:H/A:L
CNA and ADP enrichment extracted from CVE v5
These fields come from the CVE record and ADP containers, not from Glexia's Take. They preserve time-varying source decisions such as CISA SSVC, KEV status, CVSS metrics, and provider references.
CVSS vector scores
1 official scoreWe collect every scored CVSS vector available in the official CNA and ADP containers. When more than one version is present, the table keeps the source vectors side by side instead of collapsing them into the highest score.
CVSS:3.1/AV:L/AC:L/PR:L/UI:R/S:C/C:H/I:H/A:L1.56Primary CVE scoreVulnerability scoring details
Base CVSS 3.1 score
8.1HighVector: CVSS:3.1/AV:L/AC:L/PR:L/UI:R/S:C/C:H/I:H/A:L
Source materials
- CVE List V5 sourceCVE List V5
- https://github.com/Significant-Gravitas/Auto-GPT/security/advisories/GHSA-x5gj-2chr-4ch6CVE reference · x_refsource_CONFIRM
- https://github.com/Significant-Gravitas/Auto-GPT/pull/4761CVE reference · x_refsource_MISC
Products and packages named in the record
CWE details
CWE links open Glexia weakness intelligence pages with official CWE context, developer remediation guidance, and related CVE mappings.
Improper Control of Generation of Code ('Code Injection')
Improper Control of Generation of Code ('Code Injection') represents a recurring weakness pattern that can create exploitable paths when design, validation, or implementation controls are missing.