NVD / CVE Program· CNA VulnCheck

CVE-2026-61445: PraisonAI before 4.6.78 Arbitrary File Write and Command Execution

Noroxi assessment

Priority: Monitor (action score 37/100)

The sources we track (CISA KEV, Exploit-DB, Metasploit, Nuclei, GitHub) show no public exploit code or exploitation in the wild.
Probability of exploitation in the next 30 days: 0.64% (FIRST EPSS); higher than 50.7% of all records.
Anyone who can reach it over the internet can trigger it. A low-privileged account is enough. No user action is required. No special conditions are required; it is repeatable.
Fixed version: MervinPraison PraisonAI 4.6.78.
Mentioned 1 time in Turkish national cyber security advisories (siberguvenlik.gov.tr).

Low priority for now. Upgrade to MervinPraison PraisonAI 4.6.78 or later.

Generated automatically from the record's data: CVSS (NVD and CNA), CISA KEV and SSVC, FIRST EPSS, exploit sources, fixed versions. How we calculate it

Primary sources: NVD · CVE.org · FIRST EPSS

PraisonAI before 4.6.78 contains arbitrary file write and command execution vulnerabilities in the AICoder component due to missing path validation and command sanitization in LLM tool calls. Attackers can inject malicious prompts through the chat interface to write files to arbitrary filesystem locations and execute arbitrary shell commands with root privileges.

CriticalCVSS 9.4 · v4.0—No exploit Fix available

Published: Jul 11, 2026
Updated: Oct 25, 2026
EPSS: 0.6% · 50th percentile
CWE: CWE-22

Report tools

JSON

Action score

Monitor

Low priority for now.

CVSS: 37 / 40 · 9.4 / 10
CISA KEV: 0 / 30 · Not listed
EPSS: 0 / 30 · 0.6%

CISA SSVC decision

Exploitation: proof of concept
Automatable: no
Technical impact: total

Vulnrichment: CISA's decision-tree inputs.

CNA vs NVD score

NVD: —
CNA · VulnCheck: 9.4; NVD has not scored this yet; the score shown is the CNA’s.

CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H

The score given by the assigning authority versus NVD’s independent score. A gap means the severity is contested.

Get told when this record changes

Not in KEV: no record of exploitation in the wild
No public exploit code on record
A fix has been released

If any of these changes, we'll tell you in the daily email digest.

Running WordPress? Scan your site free with WP Lens

Is your version affected? Check it

Noroxi analysis

What does it mean in your environment?

The assessment above is generated automatically from the record's data; it doesn't know your environment. Our team verifies on your systems whether this vulnerability is actually exploitable and which mitigation is enough.

We use this product, ask for help

Affected systems

Is your version affected?

Pick the product and type the version you run. It's compared with this record's version ranges in your browser; the version isn't sent anywhere.

—

Versions reported by the vendor

Affected version ranges reported by the assigning authority (VulnCheck). Independent of NVD's CPE analysis and usually ahead of it.

MervinPraison PraisonAI
- 4.6.78not affected
- before 4.6.78affected · semver

Package-level exposure

OSV and GitHub Advisory data: ecosystem, package and range. SBOM matching uses this table.

Ecosystem	Package	Affected range	Fix
PyPI	praisonai	before 4.6.78	4.6.78

Same product

mervinpraison: all records

Other highest-scoring records for the same primary product.

CVE-2026-61447PraisonAI before 1.6.78 Remote Code Execution via CodeAgent
45Plan
CVE-2026-48168PraisonAI: GitHub Actions Claude workflow command injection via unquoted PR branch name
40Plan
CVE-2026-57116PraisonAI: AgentOS remains unauthenticated after GHSA-pm96 patched version and allows remote agent invocation
39Monitor

Published before and after this one in the same product

← EarlierCVE-2026-61439Jul 11, 2026 · PraisonAI before 4.6.78 Prompt Injection Defense Bypass
34Monitor
← EarlierCVE-2026-61442Jul 11, 2026 · PraisonAI Platform before 0.1.9 Authorization Bypass via PATCH
28Monitor
Later →CVE-2026-60085Jul 15, 2026 · PraisonAI before 4.6.78 Unenforced Security Policy in Subprocess Sandbox
34Monitor

Remediation

Which version to upgrade to

Fix versions compiled from the vendor, package registries and Microsoft. Verify the vendor's note before upgrading.

Product / package	Fixed version	Source
MervinPraison PraisonAI	4.6.78	Vendor (CNA)
PyPI:praisonai	4.6.78	Package registry (OSV)

Exploit status

No known public exploit

No public exploit has been observed yet. That doesn't mean you're safe, only that the bar is a little higher.

Research context

For pentesters and researchers: attack profile, score disagreement, timeline, patch commits, credits, variant and chain candidates, bug bounty scope. All derived from existing data; no exploit code.

Timeline

From publication to today: proof of concept, Metasploit module, CISA KEV and fix record. Dates are as reported by the sources.

No dated events beyond publication.

EPSS, last 120 days

FIRST EPSS daily score; only changes of 0.01 or more are recorded (step chart).

Patch and commit links

Commit, PR and diff links among the references. A starting point for patch-diffing and variant hunting; fixes, not exploits.

No commit or PR link among the references.

Credits

All researchers

Finders, reporters and analysts named in the CNA record. Click a name for that researcher’s other records.

anushkavirgaonkarreporter

Variant candidates

Same product, same weakness class, within 18 months. If the patch missed the root cause, the sibling bug is here.

CVE-2026-5714565 days apartPraisonAI: Arbitrary File Read/Write via `multiedit` Tool Without Path Validation
36Monitor
CVE-2026-614434 days apartPraisonAI before 1.6.78 Remote Code Execution via SkillTools
34Monitor
CVE-2026-4739410 days apartPraisonAI vulnerable to unauthenticated arbitrary file read via MCP workflow.show, workflow.validate, deploy.validate
34Monitor
CVE-2026-57113104 days apartPraisonAI GitHub template cache path traversal allows outside-cache file write and directory deletion
32Monitor
CVE-2026-5711965 days apartPraisonAI: Unauthenticated Local File Inclusion via agent_file path in the Jobs API
30Monitor
CVE-2026-56834104 days apartPraisonAI dynamic-context artifact tools read arbitrary host files outside artifact storage
30Monitor

Chain candidates

An authentication bypass and a privilege-requiring bug in the same product, published close together: combined they may become an unauthenticated path.

CVE-2026-614260 days apartPraisonAI before 1.7.3 Unauthenticated Agent Access via Insecure Defaults
35Monitor
CVE-2026-614280 days apartPraisonAI AgentMail before 4.6.78 Message Injection via Webhook
27Monitor
CVE-2026-614274 days apartPraisonAI before 4.6.78 Authentication Bypass via HTTP-stream
27Monitor

Bug bounty scope

No known public program.

Source: bounty-targets-data (public HackerOne, Bugcrowd, Intigriti, YesWeHack listings).

National notice (Türkiye Cybersecurity Directorate / USOM)

Official security notices citing this record; remediation advice is on the agency's page.

TR-26-0530 · Jul 13, 2026(PraisonAI Güvenlik Zafiyeti )

All national notices →

Technical details

Attack conditions

Anyone who can reach it over the internet can trigger it.
A low-privileged account is enough.
No user action is required.
No special conditions are required; it is repeatable.

If successful

Confidentiality
Integrity
Availability

Attack vector: Network
Attack complexity: Low
Privileges required: Low
User interaction: None
Scope: X

Weakness class (CWE)

CWE-22 · Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal')

CVSS vector

CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H/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

nvd-secondary

Root cause

A user-supplied file name is joined with the allowed directory, but the result is never checked to confirm it is still inside that directory.

The bug in code

The whole CWE-22 class

A representative example of this vulnerability class. Not the vendor's source code; it shows the faulty pattern and its fix.

Vulnerable

1const file = path.join(ROOT, req.query.name);
2res.sendFile(file);

Fixed

1const file = path.resolve(ROOT, req.query.name);
2if (!file.startsWith(ROOT + path.sep)) {
3  return res.sendStatus(400);
4}
5res.sendFile(file);

Attack context

MITRE CAPEC attack patterns and ATT&CK techniques for this weakness class (CWE). A starting point for detection rules and threat hunting.

Attack patterns (CAPEC)

ATT&CK techniques

—

Change log

Fix✗ → ✓Sep 28, 2026, 10:11 PM UTC

For records you follow, these changes also arrive as notifications. →

References

github.com/MervinPraison/PraisonAI/security/advisories/GHSA-9mp3-24cc-77mg

Show all references (1 more)

www.vulncheck.com/advisories/praisonai-before-arbitrary-file-write-and-command-execution

Vendor advisories and official records. Exploit/PoC links are deliberately left out.

All records