CVE-2026-44336: CWE-20: Improper Input Validation in MervinPraison PraisonAI
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 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.
AI Analysis
Technical Summary
PraisonAI's MCP server registers file-handling tools that accept path or filename strings without containment checks or input validation against the expected schema. This allows attackers to traverse directories by using path elements like "../../" in the rule_name parameter, escaping the intended rules directory. By writing malicious Python .pth files into the user site-packages directory, attackers can achieve arbitrary code execution in any Python process initiated by the user. The vulnerability is fixed in PraisonAI version 4.6.34.
Potential Impact
An attacker can write arbitrary files with the privileges of the user running PraisonAI, leading to potential arbitrary code execution on the affected system. This elevates the risk to critical severity due to the ability to execute code in subsequent Python processes, including CLI invocations, IDE scripts, REPL sessions, or background Python services.
Mitigation Recommendations
This vulnerability is patched in PraisonAI version 4.6.34. Users should upgrade to version 4.6.34 or later to remediate this issue. No other mitigation guidance is provided or necessary given the availability of an official fix.
CVE-2026-44336: CWE-20: Improper Input Validation in MervinPraison PraisonAI
Description
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 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.
CVSS v4.0
Score 9.4critical
Affected software
Run on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
PraisonAI's MCP server registers file-handling tools that accept path or filename strings without containment checks or input validation against the expected schema. This allows attackers to traverse directories by using path elements like "../../" in the rule_name parameter, escaping the intended rules directory. By writing malicious Python .pth files into the user site-packages directory, attackers can achieve arbitrary code execution in any Python process initiated by the user. The vulnerability is fixed in PraisonAI version 4.6.34.
Potential Impact
An attacker can write arbitrary files with the privileges of the user running PraisonAI, leading to potential arbitrary code execution on the affected system. This elevates the risk to critical severity due to the ability to execute code in subsequent Python processes, including CLI invocations, IDE scripts, REPL sessions, or background Python services.
Mitigation Recommendations
This vulnerability is patched in PraisonAI version 4.6.34. Users should upgrade to version 4.6.34 or later to remediate this issue. No other mitigation guidance is provided or necessary given the availability of an official fix.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- GitHub_M
- Date Reserved
- 2026-05-05T19:52:59.147Z
- Cvss Version
- 4.0
- State
- PUBLISHED
- Remediation Level
- null
Threat ID: 69fdede9cbff5d8610dd28d1
Added to database: 05/08/2026, 14:06:33 UTC
Last enriched: 05/16/2026, 10:49:49 UTC
Last updated: 07/31/2026, 19:22:59 UTC
Views: 94
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
External Links
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.