CVE-2026-34935 json
PraisonAI: OS Command Injection in MCPHandler.parse_mcp_command()
published 7mo ago modified 3mo ago also EUVD-2026-18913 , GHSA-9gm9-c8mq-vq7m , PYSEC-2026-471
- cvss
- 9.8
- version 3.1, CNA
- cisa kev
- Not listed
- not in CISA's catalog
- epss
- 0.8%
- EPSS 0.8% chance of exploitation in 30 days, percentile 58%
- public exploits
- 0
- none known
Summary
PraisonAI is a multi-agent teams system. From version 4.5.15 to before version 4.5.69, the --mcp CLI argument is passed directly to shlex.split() and forwarded through the call chain to anyio.open_process() with no validation, allowlist check, or sanitization at any hop, allowing arbitrary OS command execution as the process user. This issue has been patched in version 4.5.69.
Patch / fix
Is CVE-2026-34935 in your dependencies? Fencer shows which of your repositories are affected as soon as an advisory lands, and opens the fix as a pull request.
Check with FencerCISA SSVC
- Exploitation
- Proof of concept is public
- Automatable
- yes
- Technical impact
- total
- Assessed
- 7mo ago
Exploit prediction
0.84% chance of exploitation in the next 30 days, higher than 58% of all scored CVEs (FIRST EPSS, 2026-11-09).
Exploits and checks
- github.com https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-9gm9-c8mq-vq7m 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 | >=4.5.15, <4.5.69 |
4.5.69 |
Affected products
- MervinPraison PraisonAI
Classification
- Weakness
-
- CWE-78 Improper Neutralization of Special Elements used in an OS Command
References
-
github.com
/MervinPraison/PraisonAI/commit/47bff65413beaa3c21bf633c1fae4e684348368c
web, patch
-
github.com
/MervinPraison/PraisonAI/security/advisories/GHSA-9gm9-c8mq-vq7m
web, exploit, vendor-advisory
-
nvd.nist.gov
/vuln/detail/CVE-2026-34935
advisory
-
github.com
/MervinPraison/PraisonAI
package
-
pypi.org
/project/praisonai
package
-
github.com
/advisories/GHSA-9gm9-c8mq-vq7m
advisory
Sources
- CVE List CVE-2026-34935
- GitHub Advisory GHSA-9gm9-c8mq-vq7m
- NVD CVE-2026-34935
- OSV PYSEC-2026-471
Fencer Intel 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.