CVE-2026-61445: Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal') in MervinPraison PraisonAI
PraisonAI versions before 4.6.78 have a critical path traversal vulnerability in the AICoder component. This flaw allows attackers to write arbitrary files and execute shell commands with root privileges by injecting malicious prompts through the chat interface. The vulnerability arises from missing path validation and command sanitization in LLM tool calls. No official patch or remediation guidance is currently provided by the vendor.
AI Analysis
Technical Summary
CVE-2026-61445 describes a critical vulnerability in MervinPraison's PraisonAI product prior to version 4.6.78. The AICoder component lacks proper validation of file paths and sanitization of commands when processing prompts via the chat interface. This allows attackers to perform arbitrary file writes and execute arbitrary shell commands with root privileges, effectively compromising the system. The vulnerability is due to improper limitation of pathname to a restricted directory, commonly known as a path traversal issue combined with command injection. The CVSS 4.0 base score is 9.4, indicating critical severity. No patch or official remediation level has been disclosed as of the publication date.
Potential Impact
Successful exploitation enables attackers to write files to arbitrary locations on the filesystem and execute arbitrary shell commands with root privileges. This can lead to full system compromise, data loss, or unauthorized control over the affected system.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until an official fix is available, restrict access to the vulnerable PraisonAI instances and monitor for suspicious activity related to the AICoder component. Avoid exposing the chat interface to untrusted users.
CVE-2026-61445: Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal') in MervinPraison PraisonAI
Description
PraisonAI versions before 4.6.78 have a critical path traversal vulnerability in the AICoder component. This flaw allows attackers to write arbitrary files and execute shell commands with root privileges by injecting malicious prompts through the chat interface. The vulnerability arises from missing path validation and command sanitization in LLM tool calls. No official patch or remediation guidance is currently provided by the vendor.
CVSS v4.0
Score 9.4critical
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
CVE-2026-61445 describes a critical vulnerability in MervinPraison's PraisonAI product prior to version 4.6.78. The AICoder component lacks proper validation of file paths and sanitization of commands when processing prompts via the chat interface. This allows attackers to perform arbitrary file writes and execute arbitrary shell commands with root privileges, effectively compromising the system. The vulnerability is due to improper limitation of pathname to a restricted directory, commonly known as a path traversal issue combined with command injection. The CVSS 4.0 base score is 9.4, indicating critical severity. No patch or official remediation level has been disclosed as of the publication date.
Potential Impact
Successful exploitation enables attackers to write files to arbitrary locations on the filesystem and execute arbitrary shell commands with root privileges. This can lead to full system compromise, data loss, or unauthorized control over the affected system.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until an official fix is available, restrict access to the vulnerable PraisonAI instances and monitor for suspicious activity related to the AICoder component. Avoid exposing the chat interface to untrusted users.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- VulnCheck
- Date Reserved
- 2026-07-09T14:05:47.929Z
- Cvss Version
- 4.0
- State
- PUBLISHED
- Remediation Level
- null
Threat ID: 6a52461668715ace43df4aa1
Added to database: 07/11/2026, 13:33:10 UTC
Last enriched: 07/11/2026, 13:47:42 UTC
Last updated: 07/11/2026, 14:01:59 UTC
Views: 4
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.
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.