CVE-2026-44334 json
PraisonAI: Unauthenticated RCE via `tool_override.py`
published 2026-05-06 6 mo ago modified 2026-10-26 13 d ago also GHSA-xcmw-grxf-wjhj , PYSEC-2026-2926 , EUVD-2026-28636
- cvss
- 8.4
- version 3.1, CNA
- cisa kev
- Not listed
- not in CISA's catalog
- epss
- 0.2%
- EPSS 0.2% chance of exploitation in 30 days, percentile 16%
- public exploits
- 0
- none known
Summary
PraisonAI is a multi-agent teams system. From version 4.5.139 to before version 4.6.32, CVE-2026-40287's fix gated tools.py auto-import behind PRAISONAI_ALLOW_LOCAL_TOOLS=true in two files (tool_resolver.py, api/call.py). A third import sink in praisonai/templates/tool_override.py was missed and remains unguarded. It is reached by the recipe runner on every recipe execution and is remotely triggerable through POST /v1/recipes/run with a recipe value pointing at any local absolute path or any GitHub repo (because SecurityConfig.allow_any_github defaults to True). The attacker drops a tools.py next to TEMPLATE.yaml; the server exec_module()s it. No auth required by default, no environment opt-in required. This issue has been patched in version 4.6.32.
Patch / fix
- pypi praisonai 4.6.32
- praison praisonai 4.6.32
CISA SSVC
- Exploitation
- none
- Automatable
- no
- Technical impact
- total
- Assessed
- 6 mo ago
Exploit prediction
0.25% chance of exploitation in the next 30 days, higher than 16% of all scored CVEs (FIRST EPSS, 2026-11-08).
Exploits and checks
- github.com https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-xcmw-grxf-wjhj referenced PoC, tagged "exploit" by a source, unverified
CVSS scores
| assigned by | version | score | vector |
|---|---|---|---|
| CNA | 3.1 | 8.4 | CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
| GitHub | 3.1 | 8.4 | CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
| OSV | 3.1 | 8.4 | CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H |
Affected packages
| ecosystem | package | affected | fixed in |
|---|---|---|---|
| pypi | praisonai | >=4.5.139, <4.6.32 |
4.6.32 |
Affected products
- MervinPraison PraisonAI
Classification
- Weakness
-
- CWE-94 Improper Control of Generation of Code
References
-
github.com
/MervinPraison/PraisonAI/security/advisories/GHSA-xcmw-grxf-wjhj
web, exploit, vendor-advisory
-
nvd.nist.gov
/vuln/detail/CVE-2026-44334
advisory
-
github.com
/MervinPraison/PraisonAI
package
-
github.com
/advisories/GHSA-g985-wjh9-qxxc
advisory
-
pypi.org
/project/praisonai
package
-
github.com
/advisories/GHSA-xcmw-grxf-wjhj
advisory
Sources
- CVE List CVE-2026-44334
- GitHub Advisory GHSA-xcmw-grxf-wjhj
- NVD CVE-2026-44334
- OSV PYSEC-2026-2926
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.