Vulnerability · Published May 8, 2026 · Assigned by GitHub_M
CVE-2026-44334PraisonAI: Unauthenticated RCE via `tool_override.py`
High 8.4
In plain English
A high-severity code injection in PraisonAI from MervinPraison. There are no confirmed reports of exploitation so far. The chance it is exploited in the next 30 days is estimated at 0.2% (higher than 16% of all known vulnerabilities). Fixed versions are available - upgrade the affected package.
Official description
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.
Affected packages & fixed versions
| Ecosystem | Package | Fixed in | Advisory |
|---|---|---|---|
| PyPI | praisonai | 4.6.32 | GHSA-xcmw-grxf-wjhj |
| PyPI | praisonai | 4.6.32 | PYSEC-2026-2926 |
Affected products (as reported)
| Vendor | Product | Versions |
|---|---|---|
| MervinPraison | PraisonAI | >= 4.5.139, < 4.6.32 |
Weakness: CWE-94 · Vector: CVSS:3.1/AV:L/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H