CVE-2024-6091 — Vulnerability in agpt — CVE Details
CRITICAL
AutoGPT bypass of the shell commands denylist settings
Published September 11, 2024Updated June 29, 2026Source: osv
Summary
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.
Advisory Timeline
- First published September 11, 2024 (761 days ago).
- Last revised June 29, 2026 — 656 days after initial publication.
Affected Packages (1)
Affects 1 ecosystem: pypi (1).
| Package | Ecosystem | Affected | Fixed In |
|---|---|---|---|
| agpt | pypi | 0.2.2 | Range-based data available |
Vulnerability Classification
Common Weakness Enumeration (CWE) identifiers for this vulnerability type.
- CWE-78OS Command InjectionMITRE
CVSS Score Breakdown
What the CVSS (Common Vulnerability Scoring System) 9.8 score means for each attack dimension.
Attack Vector
Network
Attack Complexity
Low
Privileges Required
None
User Interaction
None
Scope
Unchanged
Confidentiality
High
Integrity
High
Availability
High
CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
References
Frequently Asked Questions
- What is CVE-2024-6091?
- AutoGPT bypass of the shell commands denylist settings This vulnerability has been assigned a severity rating of CRITICAL (CVSS score: 9.8/10).
- How do I check if my project is affected by CVE-2024-6091?
- CVE-2024-6091 affects agpt. Use GeekWala's free vulnerability scanner to check your dependencies against CVE-2024-6091 and 200,000+ other known vulnerabilities.
Severity & Exploitability
CVSS Score
9.8
Exploitation is straightforward and causes maximum impact. Patch immediately.
Also Known As
GHSA-g84q-54hf-36rg
PYSEC-2026-257
Related CVEs
- CVE-2026-24780CRITICAL
AutoGPT is Vulnerable to RCE via Disabled Block Execution
- CVE-2026-61447CRITICAL
PraisonAI: CodeAgent Executes LLM-Generated Code Without Sandboxing and Leaks All Environment Secrets
- CVE-2026-61445CRITICAL
PraisonAI: AICoder Arbitrary File Write and Command Execution via LLM Tool Calls
- CVE-2026-24780HIGH
AutoGPT is Vulnerable to RCE via Disabled Block Execution
Check if you're affected
Scan your dependencies to see if this vulnerability affects your projects.
Scan Your Dependencies