Skip to main content

PraisonAI EUVDEUVD-2026-43174

| CVE-2026-60088 MEDIUM
Path Traversal (CWE-22)
2026-07-11 VulnCheck GHSA-wgvq-3jxh-4qg7
6.8
CVSS 4.0 · Vendor: VulnCheck
Share

Severity by source

Vendor (VulnCheck) PRIMARY
6.8 MEDIUM
CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:P/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
vuln.today AI
5.5 MEDIUM

Local vector (AV:L) and required user interaction (UI:R) because the victim must load the crafted command file; attacker needs no privileges on the target system.

3.1 AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:N/A:N
4.0 AV:L/AC:L/AT:N/PR:N/UI:P/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N

Primary rating from Vendor (VulnCheck).

CVSS VectorVendor: VulnCheck

Attack Vector
Local
Attack Complexity
Low
Privileges Required
None
User Interaction
P
Scope
X

Lifecycle Timeline

1
Analysis Generated
Jul 11, 2026 - 14:13 vuln.today

DescriptionCVE.org

PraisonAI before 4.6.78 fails to validate file path references in custom command templates, allowing attackers to read files outside the workspace. Attackers can include path traversal sequences like @../outside_secret.txt or absolute paths in project command files to exfiltrate process-readable files into model prompts.

AnalysisAI

Path traversal in PraisonAI before 4.6.78 enables file exfiltration outside the workspace by embedding traversal sequences (e.g., @../outside_secret.txt) or absolute paths in custom project command templates, which are then injected verbatim into model prompts. Users who process attacker-controlled command files expose all process-readable files - including credentials, environment variables, and application secrets - to whoever controls the model interaction. No public exploit code has been identified and PraisonAI is not listed in the CISA KEV catalog at time of analysis; a vendor patch is available.

Technical ContextAI

PraisonAI is an open-source multi-agent AI orchestration framework (CPE: cpe:2.3:a:mervinpraison:praisonai:*:*:*:*:*:*:*:*) that allows users to define project-level command templates referencing local files via an @filename syntax. CWE-22 (Improper Limitation of a Pathname to a Restricted Directory - Path Traversal) identifies the root cause: the template parser accepts user-supplied path references without canonicalizing or bounding them to the workspace directory. As a result, sequences like @../../../etc/shadow or absolute paths like /home/user/.ssh/id_rsa are resolved against the host filesystem at the process's permission level, and the resolved file contents are silently folded into the prompt context sent to the underlying model.

RemediationAI

Upgrade PraisonAI to version 4.6.78 or later, which incorporates the fix from commit 3aa9cbc2bd49c23a32be0a89a5e620d13d843eab (https://github.com/MervinPraison/PraisonAI/commit/3aa9cbc2bd49c23a32be0a89a5e620d13d843eab). The vendor advisory at https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-xpx6-x8c2-mw5w should be consulted for release guidance. As a compensating control before patching, restrict the OS-level file permissions of sensitive files (credentials, key material, .env files) so they are not readable by the user or service account running PraisonAI - note this reduces the blast radius but does not eliminate the path traversal flaw. Additionally, avoid processing project command files from untrusted or unreviewed sources; auditing command templates for @.. or absolute-path references can identify malicious files before execution.

CVE-2026-55536 CRITICAL POC
9.1 Aug 25

WebSocket origin-validation bypass in PraisonAI's Browser Server (praisonai/browser/server.py) before 4.6.58 lets an att

CVE-2026-55541 HIGH POC
8.8 Aug 25

PraisonAI's `praisonai serve` subsystem (agents and unified modes) accepts an `--api-key` CLI flag that is parsed but ne

CVE-2026-55534 HIGH POC
8.6 Aug 25

Unauthenticated remote agent invocation in PraisonAI versions 4.6.34 through 4.6.57 allows any network-reachable caller

CVE-2026-55526 HIGH POC
8.5 Aug 25

SSRF protection bypass in PraisonAI's praisonaiagents library (all versions before 1.6.58) lets low-privileged users rou

CVE-2026-55533 HIGH POC
8.2 Aug 25

Authentication fail-open in PraisonAI's Recipe HTTP server allows unauthenticated remote attackers to invoke recipe exec

CVE-2026-55528 HIGH POC
8.2 Aug 25

Authentication bypass in PraisonAI's AgentServer component exposes all routes - /publish, /events, /info, /health - to u

CVE-2026-55522 HIGH POC
7.8 Aug 05

Arbitrary Python code execution in PraisonAI's workflow include feature allows an attacker who controls a local recipe d

CVE-2026-55523 HIGH POC
7.7 Aug 05

Server-side request forgery in PraisonAI's web_crawl() function (versions 1.5.128-1.6.57) allows an attacker who can inf

CVE-2026-55532 HIGH POC
7.6 Aug 25

Cross-site request forgery against the PraisonAI MCP HTTP-stream transport allows unauthenticated remote attackers to ex

CVE-2026-44338 HIGH POC
7.3 May 08

Remote unauthenticated access to PraisonAI's legacy Flask API server allows attackers to execute configured agent workfl

CVE-2026-55527 HIGH POC
7.1 Aug 25

Path traversal in praisonaiagents prior to 1.6.58 allows a low-privileged caller to write arbitrary JSON files to any pr

CVE-2026-55535 MEDIUM POC
6.8 Aug 25

Server-Side Request Forgery in PraisonAI before version 4.6.58 allows unauthenticated remote attackers to force the appl

Share

EUVD-2026-43174 vulnerability details – vuln.today

This site uses cookies essential for authentication and security. No tracking or analytics cookies are used. Privacy Policy