Evidence used
- No CISA KEV confirmation is currently recorded.
- Exploitation requires an existing local or physical foothold with privileges.
- EPSS is 0.35% for the current model date.
BlackTreeCVE IntelligenceFull vulnerability report · 2023
CVE-2023-37274High confidence
Python code execution sandbox escape in non-docker version in Auto-GPT
Significant-Gravitas · Auto-GPT
Official source article: GitHub GHSA-5H38-MGP9-RJ5F ↗. Check the applicable product and release in the original source.
7.6HighCVSS 3.1
Within 7 days
Patch availableHigh technical severity; prioritise exposed affected systems while verifying vendor guidance.
R
Open reassessment dashboard →Operational reassessment
Published severity in operational context
Published severityHigh→Operational priority:Medium, lowered one band.downgradedsince 30 Oct 2024
Compensating controls
- Validate the affected product branch and deploy the verified fixed release.
- Restrict local access and enforce least privilege on affected hosts.
- Monitor vendor guidance and exploitation sources for a material change.
Verification
- Confirm that the asset runs Significant-Gravitas Auto-GPT and falls inside the recorded affected range.
- Verify the installed build against the product-specific fixed version after deployment.
- Validate exposure, authentication requirements and compensating controls in the actual environment.
- Reopen this reassessment when CVSS, KEV, EPSS, exploit evidence or remediation changes.
High technical severity; prioritise exposed affected systems while verifying vendor guidance.
Patch available01
What, why and how
Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model. When Auto-GPT is executed directly on the host system via the provided run.sh or run.bat files, custom Python code execution is sandboxed using a temporary dedicated docker container which should not have access to any files outside of the Auto-GPT workspace directory. Before v0.4.3, the `execute_python_code` command (introduced in v0.4.1) does not sanitize the `basename` arg before writing LLM-supplied code to a file with an LLM-supplied name. This allows for a path traversal attack that can overwrite any .py file outside the workspace directory by specifying a `basename` such as `../../../main.py`. This can further be abused to achieve arbitrary code execution on the host running Auto-GPT by e.g. overwriting autogpt/main.py which will be executed outside of the docker environment meant to sandbox custom python code execution the next time Auto-GPT is started. The issue has been patched in version 0.4.3. As a workaround, the risk introduced by this vulnerability can be remediated by running Auto-GPT in a virtual machine, or another environment in which damage to files or corruption of the program is not a critical problem.
What
Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model. When Auto-GPT is executed directly on the host system via the provided run.sh or run.bat files, custom Python code execution is sandboxed using a temporary dedicated docker container which should not have access to any files outside of the Auto-GPT workspace directory. Before v0.4.3, the `execute_python_code` command (introduced in v0.4.1) does not sanitize the `basename` arg before writing LLM-supplied code to a file with an LLM-supplied name. This allows for a path traversal attack that can overwrite any .py file outside the workspace directory by specifying a `basename` such as `../../../main.py`. This can further be abused to achieve arbitrary code execution on the host running Auto-GPT by e.g. overwriting autogpt/main.py which will be executed outside of the docker environment meant to sandbox custom python code execution the next time Auto-GPT is started. The issue has been patched in version 0.4.3. As a workaround, the risk introduced by this vulnerability can be remediated by running Auto-GPT in a virtual machine, or another environment in which damage to files or corruption of the program is not a critical problem.
Why
Untrusted data can cross into a code-evaluation path and be interpreted as executable instructions.
How
An attacker operating through local access may attempt exploitation with low privileges. If successful, the issue may execute code or commands in the affected security context.
What
Auto-GPT is an experimental open-source application showcasing the capabilities of the GPT-4 language model. When Auto-GPT is executed directly on the host system via the provided run.sh or run.bat files, custom Python code execution is sandboxed using a temporary dedicated docker container which should not have access to any files outside of the Auto-GPT workspace directory. Before v0.4.3, the `execute_python_code` command (introduced in v0.4.1) does not sanitize the `basename` arg before writing LLM-supplied code to a file with an LLM-supplied name. This allows for a path traversal attack that can overwrite any .py file outside the workspace directory by specifying a `basename` such as `../../../main.py`. This can further be abused to achieve arbitrary code execution on the host running Auto-GPT by e.g. overwriting autogpt/main.py which will be executed outside of the docker environment meant to sandbox custom python code execution the next time Auto-GPT is started. The issue has been patched in version 0.4.3. As a workaround, the risk introduced by this vulnerability can be remediated by running Auto-GPT in a virtual machine, or another environment in which damage to files or corruption of the program is not a critical problem.
Why
Untrusted data can cross into a code-evaluation path and be interpreted as executable instructions.
How
An attacker operating through local access may attempt exploitation with low privileges. If successful, the issue may execute code or commands in the affected security context.
02
Exploit reality and attack path
CVSS severity, EPSS forecast probability, public exploit material and CISA-confirmed exploitation are separate signals.
Observed exploitation No confirmed evidence
?
Confirmed exploitation and public exploit material are separate signals. Attacks can occur without public proof-of-concept or exploit code.No CISA KEV match was present at the last successful refresh. This means no confirmation from that source, not proof of no exploitation.
Public PoC / exploit material None recorded
?
Confirmed exploitation and public exploit material are separate signals. Attacks can occur without public proof-of-concept or exploit code.No exploit-tagged reference or CISA SSVC proof-of-concept state is currently recorded. Research may still exist outside the structured feeds.
- Likely attack path
- local access → Improper Control of Generation of Code ('Code Injection') → execute code or commands in the affected security context
- Attack surface
- Local
- Privileges required
- Low: a basic authenticated account is required
- User interaction
- Required interaction required
- Attack complexity
- High: exploitation depends on specific conditions
- Security boundary
- Changed: exploitation can affect a different security authority
- Weakness
?
CWE means Common Weakness Enumeration: a standard category for the underlying weakness. - CWE-94 ↗
CWE-94: Improper Control of Generation of Code ('Code Injection'). The product constructs all or part of a code segment using externally-influenced input from an upstream component, but it does not neutralize or incorrectly neutralizes special elements that could modify the syntax or behavior of the intended code segment.
- CVSS vector
?
CVSS means Common Vulnerability Scoring System. The vector records the metric values used to calculate technical severity. CVSS:3.1/AV:L/AC:H/PR:L/UI:R/S:C/C:H/I:H/A:HCommon Vulnerability Scoring System 3.1: the compact vector below is decoded into plain language.
AVLocalAttack vector: The attacker needs local access to the vulnerable system.ACHighAttack complexity: Successful exploitation depends on specific conditions outside the attacker's direct control.PRLowPrivileges required: The attacker needs basic user-level privileges.UIRequiredUser interaction: Another user must perform an action for exploitation to succeed.SChangedScope: The attack can affect a component governed by a different security authority.CHighConfidentiality impact: A successful attack can cause a major loss.IHighIntegrity impact: A successful attack can cause a major loss.AHighAvailability impact: A successful attack can cause a major loss.- Post-exploitation / living off the land
- After compromise, an attacker may use built-in shells, scripting engines, scheduled tasks and native network utilities for discovery, persistence or movement. This is a plausible LoTL path, not evidence that it has occurred for every attack.
03
Patch and workaround
Operational remediation based on structured source evidence.
- Status
?
Patch availability is based on structured fixed-version fields and authoritative update references. If no fix is verified, check the vendor advisory before making a change. - Patch available
- Affected
- Auto-GPT: < 0.4.3
- Action
- Review the linked authoritative reference and apply the recorded fixed release appropriate to the affected product branch.
- Workaround
- No verified workaround is recorded. Limit untrusted access and use least privilege until authoritative guidance is available.
04
Evidence and provenance
Published 13 Jul 2023 · Last source change 30 Oct 2024, 15:53 UTC · CWE-94 · Improper Control of Generation of Code ('Code Injection')
CVE recordCVE.org · 5.1
CVSS sourceCNA
EPSS source FIRST · tracked since 2026-08-14
?
The date BlackTree first stored a score for this CVE from the daily FIRST EPSS feed.European sourceENISA EUVD · EUVD-2023-41185
Product sourceCNA
Remediation sourceCVE/CNA references
CWE sourceCNA
NVD statusNVD enriched
Core structured fields are present and their contributing authorities are shown above.
Material change intelligence
View recent updates ↗What changed after publication
No material field changes have been recorded since change tracking began. Routine source refreshes and cosmetic edits are intentionally excluded.
CVE published
Fixed release or patch reference recorded
Technical terms and abbreviations used in this report
- CVE
- Common Vulnerabilities and Exposures: the public identifier for one disclosed vulnerability.
- CVSS
- Common Vulnerability Scoring System: a technical severity framework; it is not patching priority by itself.
- EPSS
- Exploit Prediction Scoring System: FIRST's estimate of the probability that exploitation activity will be observed in the next 30 days; it is a forecast, not confirmation.
- CWE
- Common Weakness Enumeration: the standard category describing the underlying software or hardware weakness.
- CNA
- CVE Numbering Authority: an organisation authorised to assign and publish CVE records.
- CISA ADP
- Cybersecurity and Infrastructure Security Agency Authorized Data Publisher: structured enrichment added to a CVE record.
- NVD
- National Vulnerability Database: NIST's enrichment service for CVE records.
- CERT / CSIRT
- A computer security incident response team that publishes warnings or coordinates incident response.
- PoC
- Proof of concept: public material that demonstrates or helps reproduce exploitation.
- CSAF
- Common Security Advisory Framework: a machine-readable format for security advisories.
- LoTL
- Living off the land: abuse of legitimate tools or system functions during an attack.