CVE-2024-6091 json
Shell Command Denylist Bypass in significant-gravitas/autogpt
published 2024-09-11 2 y ago modified 2026-10-26 13 d ago also GHSA-g84q-54hf-36rg , PYSEC-2026-257 , EUVD-2024-2796
- cvss
- 9.8
- version 3.0, CNA
- cisa kev
- Not listed
- not in CISA's catalog
- epss
- 0.8%
- EPSS 0.8% chance of exploitation in 30 days, percentile 57%
- public exploits
- 0
- none known
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.
Patch / fix
- significant-gravitas significant-gravitas/autogpt 0.5.1
- significant-gravitas autogpt 0.5.1
CISA SSVC
- Exploitation
- Proof of concept is public
- Automatable
- yes
- Technical impact
- total
- Assessed
- 2 y ago
Exploit prediction
0.82% chance of exploitation in the next 30 days, higher than 57% of all scored CVEs (FIRST EPSS, 2026-11-08).
Exploits and checks
- huntr.com https://huntr.com/bounties/8a742c13-bb5e-4bc9-8b86-049d8a386050 referenced PoC, tagged "exploit" by a source, unverified
CVSS scores
| assigned by | version | score | vector |
|---|---|---|---|
| CNA | 3.0 | 9.8 | CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
| NVD | 3.1 | 9.8 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
| OSV | 3.0 | 9.8 | CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
| GitHub | 3.0 | 9.8 | CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
Affected packages
| ecosystem | package | affected | fixed in |
|---|---|---|---|
| pypi | agpt | <=0.5.1 |
no fix listed |
Affected products
- significant-gravitas significant-gravitas/autogpt
- significant-gravitas autogpt
Classification
- Weakness
-
- CWE-78 Improper Neutralization of Special Elements used in an OS Command
References
-
github.com
/significant-gravitas/autogpt/commit/ef691359b774a1f9f80cf4f5ace9821967b718ed
web, patch
-
huntr.com
/bounties/8a742c13-bb5e-4bc9-8b86-049d8a386050
web, exploit, third-party-advisory
-
nvd.nist.gov
/vuln/detail/CVE-2024-6091
advisory
-
github.com
/Significant-Gravitas/AutoGPT
package
-
github.com
/pypa/advisory-database/tree/main/vulns/agpt/PYSEC-2026-257.yaml
web
-
pypi.org
/project/agpt
web, package
-
github.com
/advisories/GHSA-g84q-54hf-36rg
advisory
Sources
- CVE List CVE-2024-6091
- GitHub Advisory GHSA-g84q-54hf-36rg
- NVD CVE-2024-6091
- OSV PYSEC-2026-257
Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.