CVE-2026-44334 | PraisonAI: Unauthenticated RCE via `tool_override.py`

Exp

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.

Published: 2026-05-08 Last update: 2026-05-08 Assigner: [email protected] Source: [email protected]
NVD Status：Analyzed，CVE State: published
View at NVD, CVE.org, EUVD

CVE-2026-44334 is rated Exploit Available (50.2/100): CVSS High severity, with low exploitation likelihood (EPSS 0.02%). 1 public exploit reference(s) are indexed (Exploit-DB). Public exploits are available—assess exposure, apply mitigations, and prioritize patching.

Risk is dynamic; we continuously reassess and refresh what is shown on this page as upstream context changes.

Public exploit references (Exploit-DB) for CVE-2026-44334

EDB-ID Source Kind Published Link
— nvd_ref exploit_tag Exploit-DB ↗

Exploit prediction scoring system (EPSS) score for CVE-2026-44334

EPSS lead: Daily EPSS estimates relative likelihood of exploitation; percentile ranks this CVE among scored vulnerabilities (higher = more severe relative rank).

# Date Old EPSS score New EPSS score Delta (New - Old)
1 2026-05-09 — 0.02% —

Full EPSS history (1 record total)

Common vulnerability scoring system (CVSS) metrics for CVE-2026-44334

CVSS metrics for this CVE.

Base score Version Severity Vector Exploitability Impact Score source
8.4 3.1 HIGH
CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H Click to expand
Attack vector (AV:L)
They already need access on the box, or another person has to do something wrong; it’s not a remote drive-by.
Attack complexity (AC:L)
Once they can reach the bug, pulling it off is straightforward—no weird race conditions or rare setup.
Privileges required (PR:N)
No account or special rights needed—anonymous or random user is enough.
User interaction (UI:N)
Nobody has to click “OK” or open a trap file; it can work without a victim helping.
Scope (S:U)
Damage stays in the same “trust bubble” as the broken component—no big spill into unrelated systems.
Confidentiality (C:H)
Serious risk that confidential data gets exposed in a big way.
Integrity (I:H)
They could widely tamper with or forge data—trust in the data is badly hurt.
Availability (A:H)
Could take the service down hard or make it unusable for people who depend on it.
 2.5 5.9 [email protected]

Weakness enumeration for CVE-2026-44334

GitHub Security Advisory for CVE-2026-44334

GHSA-xcmw-grxf-wjhj · Severity: high · Ecosystem: pip — PraisonAI has unauthenticated RCE via `tool_override.py` (CVE-2026-40287 patch bypass)

Affected software / configurations for CVE-2026-44334

Vendor Product Version Raw CPE
praison praisonai >= 4.5.139, < 4.6.32 cpe:2.3:a:praison:praisonai:*:*:*:*:*:*:*:*

References for CVE-2026-44334

cvelogic Threat Intelligence