Skip to main content

CVE-2026-56834: CWE-22: Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal') in MervinPraison PraisonAI

0
High
VulnerabilityCVE-2026-56834cvecve-2026-56834cwe-22cwe-200
Published: 10/23/2026 (10/23/2026, 11:56:40 UTC)
Source: CVE Database V5
Vendor/Project: MervinPraison
Product: PraisonAI

Description

PraisonAI versions from 3.8.1 up to but not including 4.6.59 contain a path traversal vulnerability in the Dynamic Context Discovery feature. This flaw allows unauthorized reading of arbitrary files on the host filesystem by manipulating artifact tool arguments. The vulnerability arises because the artifact tools do not verify that the supplied paths are within the configured artifact base directory or created by the configured store. This can expose sensitive files such as .env files, cloud credentials, SSH keys, and source code. The issue is fixed in version 4.6.59.

CVSS v3.1

Score 7.5high

Attack Vector
Network
Attack Complexity
Low
Privileges Required
None
User Interaction
None
Scope
Unchanged
Confidentiality
High
Integrity
None
Availability
None
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N

Affected software

MervinPraison

PraisonAI

Affected versions
>=3.8.1 <4.6.59
GitHub Actionsmore threats →ai
mervinpraison/PraisonAI
pkg:github/mervinpraison/PraisonAI

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

AILast updated: 10/23/2026, 12:30:38 UTC

Technical Analysis

CVE-2026-56834 is a path traversal vulnerability (CWE-22) in MervinPraison's PraisonAI product affecting versions >=3.8.1 and <4.6.59. The Dynamic Context Discovery feature exposes artifact helper tools via ctx.get_tools(), which accept user-supplied paths without enforcing that these paths reside within the configured artifact base directory or are created by the configured store. The artifact tools artifact_head, artifact_tail, artifact_grep, and artifact_chunk directly wrap the user-supplied path into an ArtifactRef and read from the host filesystem. This allows an attacker who can influence these tool arguments to read arbitrary files accessible to the PraisonAI process, potentially leaking sensitive information such as environment variables, credentials, SSH keys, and source files. The vulnerability has been patched in version 4.6.59.

Potential Impact

An unauthenticated attacker or any user able to influence the artifact tool arguments can read arbitrary files on the host system with the privileges of the PraisonAI process. This can lead to disclosure of sensitive information including project environment variables, cloud credentials, SSH keys, and source code. There is no impact on integrity or availability reported. The CVSS v3.1 score is 7.5 (High), reflecting the network attack vector, low attack complexity, no privileges required, no user interaction, and high confidentiality impact.

Mitigation Recommendations

Upgrade PraisonAI to version 4.6.59 or later, where this path traversal vulnerability has been fixed. The patch enforces proper validation of artifact paths to ensure they reside within the configured artifact base directory and are created by the configured store. Until upgrading, restrict access to the Dynamic Context Discovery feature and limit who can supply artifact tool arguments to trusted users only.

Pro Console: star threats, build custom feeds, automate alerts via Slack, email & webhooks.Upgrade to Pro

Technical Details

Data Version
5.2
Assigner Short Name
GitHub_M
Date Reserved
2026-06-23T14:55:09.117Z
Cvss Version
3.1
State
PUBLISHED

Threat ID: 6adb50114d27ba8daa216e8b

Added to database: 10/23/2026, 12:16:17 UTC

Last enriched: 10/23/2026, 12:30:38 UTC

Last updated: 10/23/2026, 15:26:05 UTC

Views: 5

Community Reviews

0 reviews

Crowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.

Sort by
Loading community insights…

Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.

Actions

PRO

Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.

Please log in to the Console to use AI analysis features.

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

Breach by OffSeqOFFSEQFRIENDS — 25% OFF

Check if your credentials are on the dark web

Instant breach scanning across billions of leaked records. Free tier available.

Scan now
OffSeq TrainingCredly Certified

Lead Pen Test Professional

Technical5-day eLearningPECB Accredited
View courses