Skip to content
Noroxi
CVE.org (no NVD analysis yet)· CNA GitHub_M

CVE-2026-56838: PraisonAI recipe.run_stream skips dangerous-tool policy enforcement

HighCVSS 7.8 · v3.1—No exploit Fix available

Noroxi assessment

Priority: Monitor (action score 31/100)

  • 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: 0.14% (FIRST EPSS).
  • Someone with local access to the system can trigger it. No account or password is required. A user must open a link or visit a page. No special conditions are required; it is repeatable.
  • Fixed version: MervinPraison PraisonAI 4.6.59.
  • Mentioned 1 time in Turkish national cyber security advisories (siberguvenlik.gov.tr).

Low priority for now. Upgrade to MervinPraison PraisonAI 4.6.59 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 is a multi-agent teams system. From version 4.5.87 to before version 4.6.59, PraisonAI recipe execution blocks default-denied dangerous tools unless the caller explicitly passes allow_dangerous_tools=True. The normal recipe.run() path enforces this with _check_tool_policy(). The streaming path, recipe.run_stream(), loads the same recipe, checks dependencies, and then calls _execute_recipe() without running the dangerous-tool policy check. As a result, a recipe that honestly declares execute_command in TEMPLATE.yaml requires.tools is denied by recipe.run(), but reaches the execution engine through recipe.run_stream() with allow_dangerous_tools=False. This issue has been patched in version 4.6.59.

Published
Oct 23, 2026
Updated
Oct 29, 2026
EPSS
0.1% · 3th percentile

Report tools

JSON

Action score

31

Monitor

Low priority for now.

CVSS
31 / 40 · 7.8 / 10
CISA KEV
0 / 30 · Not listed
EPSS
0 / 30 · 0.1%

CISA SSVC decision

Exploitation
proof of concept
Automatable
no
Technical impact
total

Vulnrichment: CISA's decision-tree inputs.

CNA vs NVD score

NVD
—
CNA · GitHub_M
7.8
NVD has not scored this yet; the score shown is the CNA’s.

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.

Follow CVE-2026-56838

When you'll hear from us

  • when it enters CISA KEV
  • when exploit code appears or is weaponized
  • when the record is updated (including a fixed version)
  • when EPSS rises 20 points in a week

One daily email digest (06:00 UTC); connect a webhook for KEV listings and weaponized exploits every 10 minutes on paid plans, on the hour on the free plan.

Your free account also gets you

  • CVE alerts: add the products and versions you run, get the new CVEs that affect them
  • Uptime monitoring: 1 site, instant email when it goes down
  • Add your domain: subdomains and takeover risk scanned every week (1 domain)
  • 10 scans an hour on the security tools, at most 30 a day (3 a day without an account), an API key and MCP
  • All your scans in one panel: findings, what changed in the last scan, a report per domain or per client (PDF, share link)
All free tools

Sign up with email · Have an account? Sign in

Free account, no card. Unfollow any time.

Don't want an account? Get "Exploited this week" by email every MondayDon't want an account? RSS feed for mervinpraison records
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 (GitHub_M). Independent of NVD's CPE analysis and usually ahead of it.

  • MervinPraison PraisonAI

    • >= 4.5.87, < 4.6.59affected

Package-level exposure

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

EcosystemPackageAffected rangeFix
PyPIpraisonaifrom 4.5.87 · before 4.6.594.6.59

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-2026-56836Oct 23, 2026 · PraisonAI recipe serve Typer command bypasses the non-localhost authentication guard
    32Monitor
  • ← EarlierCVE-2026-56837Oct 23, 2026 · PraisonAI LinearBot processes unsigned webhooks when LINEAR_WEBHOOK_SECRET is missing
    34Monitor
  • Later →CVE-2026-56840Oct 23, 2026 · PraisonAI: HTTPApproval dashboard renders tool arguments as raw HTML, allowing approval-page XSS to approve dangerous tools
    35Monitor

Remediation

Which version to upgrade to

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

Product / packageFixed versionSource
MervinPraison PraisonAI4.6.59 · descriptionVendor (CNA)
PyPI:praisonai4.6.59Package 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.

  1. Published
  2. Fix recordedsame day
  3. TodayNov 12, 2026+20 d
EPSS, last 120 days

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

Variant candidates

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

  • CVE-2026-5712439 days apartPraisonAI UI MCP connect endpoint allows unauthenticated local command execution
    39Monitor
  • CVE-2026-571170 days apartPraisonAI: Compute-bridged file tools allow shell command injection
    35Monitor
  • CVE-2026-5713338 days apartPraisonAI utility shell safe-command wrapper allowlist bypass via shell chaining
    35Monitor
  • CVE-2026-5713638 days apartPraisonAI SandboxExecutor allowedCommands bypass via shell chaining
    35Monitor
  • CVE-2026-61434105 days apartPraisonAI before 4.6.78 Allowlist Bypass via find -exec
    34Monitor
  • CVE-2026-571420 days apartPraisonAI recipe workflow policy can be bypassed by declaring and YAML-approving dangerous tools outside TEMPLATE.yaml
    31Monitor

National notice (Türkiye Cybersecurity Directorate / USOM)

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

All national notices →

Not on record for this CVE: patch commit or PR link · researcher credit · public bounty program.

Technical details

Attack conditions

  • Someone with local access to the system can trigger it.
  • No account or password is required.
  • A user must open a link or visit a page.
  • No special conditions are required; it is repeatable.

If successful

Confidentiality
high · data can be read
Integrity
high · data or configuration can be modified
Availability
high · the service can be disrupted
Attack vector
Local
Attack complexity
Low
Privileges required
None
User interaction
Required
Scope
Unchanged
Confidentiality impact
High
Integrity impact
High
Availability impact
High

Weakness class (CWE)

CWE-78 · Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')

CVSS vector

CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

nvd-secondary

Root cause

User input is inserted as text into a shell command. The shell may interpret special characters in the input as part of the command.

The bug in code

The whole CWE-78 class

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

Vulnerable

ts
const host = req.body.host;exec("ping -c 1 " + host, onResult);

Fixed

ts
const host = req.body.host;if (!/^[a-z0-9.-]{1,253}$/i.test(host)) return res.sendStatus(400);execFile("ping", ["-c", "1", host], onResult);

Attack context

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

ATT&CK techniques

—

Change log

  1. SSVC exploitation— → poc
  2. Exploit maturity— → none
  3. Fix✗ → ✓

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

References

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

All records