CVE-2026-57125 json
PraisonAI: Unauthenticated RCE via Jobs API + Approval Bypass
published 2026-06-18 4 mo ago modified 2026-09-15 55 d ago also EUVD-2026-77531 , GHSA-4869-x4pr-q22x , PYSEC-2026-3501 , PYSEC-2026-3529
- cvss
- 9.8
- version 3.1, CNA
- cisa kev
- Not listed
- not in CISA's catalog
- epss
- 0.6%
- EPSS 0.6% chance of exploitation in 30 days, percentile 49%
- public exploits
- 0
- none known
Summary
PraisonAI is a multi-agent teams system. Prior to praisonai 4.6.59 and praisonaiagents 1.6.59, the unauthenticated POST /api/v1/runs Jobs API accepts attacker-controlled agent_yaml, and the approve field can mark execute_command as YAML-approved before @require_approval checks critical tools. This chain allows a remote caller to cause a configured language model agent to invoke arbitrary operating-system commands without credentials or operator interaction. This vulnerability is fixed in praisonai 4.6.59 and praisonaiagents 1.6.59 as fixed versions.
Patch / fix
- pypi praisonai 4.6.59
- pypi praisonaiagents 1.6.59
- praison praisonai 4.6.59
- praison praisonaiagents 1.6.59
CISA SSVC
- Exploitation
- Proof of concept is public
- Automatable
- yes
- Technical impact
- total
- Assessed
- 55 d ago
Exploit prediction
0.60% chance of exploitation in the next 30 days, higher than 49% of all scored CVEs (FIRST EPSS, 2026-11-08).
Exploits and checks
- github.com https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-4869-x4pr-q22x referenced PoC, tagged "exploit" by a source, unverified
CVSS scores
| assigned by | version | score | vector |
|---|---|---|---|
| CNA | 3.1 | 9.8 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
| GitHub | 3.1 | 9.8 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
| OSV | 3.1 | 9.8 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
Affected packages
| ecosystem | package | affected | fixed in |
|---|---|---|---|
| pypi | praisonai | <4.6.59 |
4.6.59 |
| pypi | praisonaiagents | <1.6.59 |
1.6.59 |
Affected products
- MervinPraison PraisonAI
- MervinPraison praisonaiagents
Classification
References
- github.com /MervinPraison/PraisonAI/commit/2adfe7e8323f6deec66925cf15a885b6238895e9
-
github.com
/MervinPraison/PraisonAI/security/advisories/GHSA-4869-x4pr-q22x
exploit, web
- github.com /MervinPraison/PraisonAI/releases/tag/v4.6.59
-
github.com
/MervinPraison/PraisonAI
package
-
pypi.org
/project/praisonai
package
-
github.com
/advisories/GHSA-4869-x4pr-q22x
advisory
-
nvd.nist.gov
/vuln/detail/CVE-2026-57125
advisory
-
pypi.org
/project/praisonaiagents
package
Sources
- CVE List CVE-2026-57125
- GitHub Advisory GHSA-4869-x4pr-q22x
- NVD CVE-2026-57125
- OSV PYSEC-2026-3501
- OSV PYSEC-2026-3529
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.
CPEs and fixed versions use Anchore's correction of NVD's data: Added CPE configurations because not yet analyzed by NVD.