CVE-2026-56839
Received
Received - Intake
Path Traversal in PraisonAI Prior to 4.6.59
Vulnerability report for CVE-2026-56839, including description, CVSS score, EPSS score, affected products, exploitability, helpful resources, and attack-flow context.
Publication date: 2026-09-14
Last updated on: 2026-09-14
Assigner: GitHub, Inc.
Description
Description
PraisonAI is a multi-agent teams system. Prior to 4.6.59, the CODE_TOOLS wrappers keep _workspace_root as None and pass workspace=None to read_file, search_replace, and apply_diff helpers that enforce path containment only for a truthy workspace. An application that exposes code_read_file, code_search_replace, or code_apply_diff before set_workspace can therefore let prompt-influenced calls read and modify files outside the intended project directory, while explicitly configured workspaces remain effective. This vulnerability is fixed in 4.6.59.
CVSS Scores
EPSS Scores
| Probability: | |
| Percentile: |
Meta Information
Affected Vendors & Products
| Vendor | Product | Version / Range |
|---|---|---|
| praisonai | praisonai | to 4.6.59 (inc) |
| mervinpraison | praisonai | to 4.6.59 (exc) |
| mervinpraison | praisonai | 4.6.59 |
Helpful Resources
Exploitability
| CWE ID | Description |
|---|---|
| CWE-22 | The product uses external input to construct a pathname that is intended to identify a file or directory that is located underneath a restricted parent directory, but the product does not properly neutralize special elements within the pathname that can cause the pathname to resolve to a location that is outside of the restricted directory. |
| CWE-863 | The product performs an authorization check when an actor attempts to access a resource or perform an action, but it does not correctly perform the check. |
| CWE-200 | The product exposes sensitive information to an actor that is not explicitly authorized to have access to that information. |