CVE-2026-44336
Published: 08 May 2026
Summary
CVE-2026-44336 is a critical-severity Improper Input Validation (CWE-20) vulnerability in Praison Praisonai. Its CVSS base score is 9.4 (Critical).
Operationally, exploitation aligns with the MITRE ATT&CK technique Exploit Public-Facing Application (T1190); ranked at the 45.2th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog; a public proof-of-concept is referenced.
This vulnerability is AI-related — categorised as AI Agent Protocols and Integrations; in the Protocol-Specific Risks risk domain.
OWASP Top 10 for Web (2025)
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2026-28639
Vulnerability details
PraisonAI is a multi-agent teams system. Prior to version 4.6.34, PraisonAI's MCP (Model Context Protocol) server (praisonai mcp serve) registers four file-handling tools by default — praisonai.rules.create, praisonai.rules.show, praisonai.rules.delete, and praisonai.workflow.show. Each accepts a path or filename string from MCP…
more
tools/call arguments and joins it onto ~/.praison/rules/ (or, for workflow.show, accepts an absolute path) with no containment check. The JSON-RPC dispatcher passes params["arguments"] blind to each handler via **kwargs without validating against the advertised input schema. By setting rule_name="../../<some-path>" an attacker walks out of the rules directory and writes any file the running user can write. Dropping a Python .pth file into the user site-packages directory escalates this primitive to arbitrary code execution in any subsequent Python process the user spawns — the next praisonai CLI invocation, an IDE script run, the user's python REPL, or any background Python service. This issue has been patched in version 4.6.34.
- CWE(s)
AI Security AnalysisAI
- AI Category
- AI Agent Protocols and Integrations
- Risk Domain
- Protocol-Specific Risks
- OWASP Top 10 for LLMs 2025
- None mapped
- Classification Reason
- Matched keywords: mcp, model context protocol
Related Threats
MITRE ATT&CK Enterprise TechniquesAI
Why these techniques?
Path traversal in exposed MCP file tools enables arbitrary file write leading to Python code execution via .pth hijack.
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.
Directly implements checks on information inputs to reject invalid data before processing.
Defining acceptable mobile code technologies and authorizing their use prevents inclusion of functionality from untrusted control spheres.
Isolated execution prevents functionality from an untrusted sphere from affecting the real environment, allowing safe behavioral inspection.
Limiting P2P file sharing technology reduces inclusion of functionality or resources from untrusted external control spheres.
Enforcing installation policies prevents users from including functionality obtained from untrusted control spheres.
The inventory process requires identifying and recording the origin of all components, making inclusion of functionality from untrusted control spheres easier to detect during reviews.
Requiring approval and monitoring of maintenance tools prevents inclusion and execution of functionality obtained from untrusted sources.
Unowned portable devices represent untrusted control spheres; the prohibition prevents inclusion of functionality or data from such sources.