CVE-2024-6091 | Shell Command Denylist Bypass in significant-gravitas/autogpt

Exp

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.

Published: 2024-09-11 Last update: 2025-08-05 Assigner: [email protected] Source: [email protected]
NVD Status：Analyzed，CVE State: published
View at NVD, CVE.org, EUVD

CVE-2024-6091 is rated High Exploit Risk (67.9/100): CVSS Critical severity, with low exploitation likelihood (EPSS 0.18%). 1 public exploit reference(s) are indexed (Exploit-DB). Public exploits are available—assess exposure, apply mitigations, and prioritize patching.

Risk is dynamic; we continuously reassess and refresh what is shown on this page as upstream context changes.

Public exploit references (Exploit-DB) for CVE-2024-6091

EDB-ID Source Kind Published Link
— nvd_ref exploit_tag Exploit-DB ↗

Exploit prediction scoring system (EPSS) score for CVE-2024-6091

EPSS lead: Daily EPSS estimates relative likelihood of exploitation; percentile ranks this CVE among scored vulnerabilities (higher = more severe relative rank).

# Date Old EPSS score New EPSS score Delta (New - Old)
1 2026-01-31 0.13% 0.18% +0.05%
2 2025-11-21 0.44% 0.13% -0.31%
3 2025-11-18 — 0.44% —

Full EPSS history (15 records total)

Common vulnerability scoring system (CVSS) metrics for CVE-2024-6091

CVSS metrics for this CVE.

Base score Version Severity Vector Exploitability Impact Score source
9.8 3.1 CRITICAL
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H Click to expand
Attack vector (AV:N)
Could be attacked over the internet or any normal routed network—not just someone sitting at the machine.
Attack complexity (AC:L)
Once they can reach the bug, pulling it off is straightforward—no weird race conditions or rare setup.
Privileges required (PR:N)
No account or special rights needed—anonymous or random user is enough.
User interaction (UI:N)
Nobody has to click “OK” or open a trap file; it can work without a victim helping.
Scope (S:U)
Damage stays in the same “trust bubble” as the broken component—no big spill into unrelated systems.
Confidentiality (C:H)
Serious risk that confidential data gets exposed in a big way.
Integrity (I:H)
They could widely tamper with or forge data—trust in the data is badly hurt.
Availability (A:H)
Could take the service down hard or make it unusable for people who depend on it.
 3.9 5.9 [email protected]
9.8 3.0 CRITICAL
CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H Click to expand
Attack vector (AV:N)
Could be attacked over the internet or any normal routed network—not just someone sitting at the machine.
Attack complexity (AC:L)
Once they can reach the bug, pulling it off is straightforward—no weird race conditions or rare setup.
Privileges required (PR:N)
No account or special rights needed—anonymous or random user is enough.
User interaction (UI:N)
Nobody has to click “OK” or open a trap file; it can work without a victim helping.
Scope (S:U)
Damage stays in the same “trust bubble” as the broken component—no big spill into unrelated systems.
Confidentiality (C:H)
Serious risk that confidential data gets exposed in a big way.
Integrity (I:H)
They could widely tamper with or forge data—trust in the data is badly hurt.
Availability (A:H)
Could take the service down hard or make it unusable for people who depend on it.
 3.9 5.9 [email protected]

Weakness enumeration for CVE-2024-6091

GitHub Security Advisory for CVE-2024-6091

GHSA-g84q-54hf-36rg · Severity: critical · Ecosystem: pip — AutoGPT bypass of the shell commands denylist settings

Affected software / configurations for CVE-2024-6091

Vendor Product Version Raw CPE
agpt autogpt_classic 0.5.1 cpe:2.3:a:agpt:autogpt_classic:0.5.1:*:*:*:*:*:*:*

References for CVE-2024-6091

cvelogic Threat Intelligence