---
title: "CVE-2024-6091: AutoGPT bypass of the shell commands denylist settings"
url: https://erroneo.us/security/cve/CVE-2024-6091/
description: "CVE-2024-6091 (agpt (PyPI)): A vulnerability in significant-gravitas/autogpt version 0.5.1 allows an attacker to bypass the shell commands denylist…"
type: vulnerability-record
section: "Security Digest"
date_published: 2024-09-11
date_modified: 2024-09-18
publisher: erroneo.us
author: erroneo.us Security Desk
cve: "CVE-2024-6091"
kev: false
cvss: 9.3
epss: 0.00819
license: All rights reserved. Quote with attribution and a link.
---

# CVE-2024-6091: AutoGPT bypass of the shell commands denylist settings

**Signal:** Critical and remotely reachable. No known exploitation yet, but it is network-reachable without credentials. (Computed from CISA KEV, EPSS and CVSS; not an editorial verdict.)

## Should you act?

- Not in CISA KEV , but CISA’s SSVC assessment records a public proof-of-concept, so attack code exists.
- EPSS 0.8% , percentile 57: FIRST’s model estimates a 0.8% chance of exploitation activity in the next 30 days, higher than 57% of all scored CVEs (moderate). EPSS is a probability, not a verdict.
- Remotely reachable with no login and no user interaction. If the vulnerable service is exposed to the internet, prioritize it.
- Only applies if your dependency tree includes agpt (PyPI) <= 0.5.1, no fixed version listed . Check your lockfile, including transitive dependencies.

## What it is

A vulnerability in significant-gravitas/autogpt version 0.5.1 allows an attacker to bypass the shell commands denylist settings. The issue arises when the denylist is configured to block specific commands, such as 'whoami' and '/bin/whoami'. An attacker can circumvent this restriction by executing commands with a modified path, such as '/bin/./whoami', which is not recognized by the denylist.

## Affected packages

- PyPI `agpt` <= 0.5.1 → fixed: none listed

## Affected products (CVE record)

- significant-gravitas significant-gravitas/autogpt: unspecified < 0.5.1

## Severity

- @huntr_ai CVSS 3.0: 9.8 `CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H`
- GitHub CVSS 4.0: 9.3 `CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N`

## Exploitation

- CISA KEV: not listed (no confirmed in-the-wild exploitation known to CISA).
- CISA SSVC assessment: exploitation poc , automatable yes , technical impact total .
- FIRST EPSS (model of 2026-10-21): 0.82% probability of exploitation activity in the next 30 days; percentile 57.

## Sources

- [GitHub Advisory GHSA-g84q-54hf-36rg](https://github.com/advisories/GHSA-g84q-54hf-36rg)
- [CVE.org record CVE-2024-6091](https://www.cve.org/CVERecord?id=CVE-2024-6091)
- [NVD entry CVE-2024-6091](https://nvd.nist.gov/vuln/detail/CVE-2024-6091)
- [huntr.com](https://huntr.com/bounties/8a742c13-bb5e-4bc9-8b86-049d8a386050)
- [github.com](https://github.com/significant-gravitas/autogpt/commit/ef691359b774a1f9f80cf4f5ace9821967b718ed)

---
Source page: https://erroneo.us/security/cve/CVE-2024-6091/ · Security Digest: https://erroneo.us/security/ · More: https://erroneo.us/llms.txt