CVE-2026-44334
Published: 08 May 2026
Summary
CVE-2026-44334 is a high-severity Code Injection (CWE-94) vulnerability in Praison Praisonai. Its CVSS base score is 8.4 (High).
Operationally, exploitation aligns with the MITRE ATT&CK technique Exploit Public-Facing Application (T1190); ranked at the 15.8th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog; a public proof-of-concept is referenced.
OWASP Top 10 for Web (2025)
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2026-28636
Vulnerability details
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…
more
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.
- CWE(s)
Related Threats
MITRE ATT&CK Enterprise TechniquesAI
Why these techniques?
Vulnerability enables unauthenticated remote code execution (CWE-94) via unguarded exec_module on a public web endpoint (/v1/recipes/run), directly mapping to public-facing app exploitation and Python interpreter abuse.
CVEs Like This One
Affected Assets
Mitigating Controls
Likely Mitigating Controls AI
Per-CVE control mapping for this CVE has not run yet; the list below is derived from the weakness types (CWEs) cited in the NVD entry.
Makes persistent code injection into loaded programs impossible when the executable image itself resides on hardware-protected read-only media.
Dynamically generated code can be produced and executed inside the isolated chamber, preventing host compromise from code-injection payloads.
Validates inputs used in dynamic code generation to block injected directives.
Directly prevents execution of attacker-supplied code written into data memory regions.