CVE Intelligence
Critical Injection

CVE-2026-47391 — PraisonAI's unauthenticated A2A official example can reach real LLM-driven `eval()` tool execution

PraisonAI is a multi-agent teams system. Prior to version 4.6.40, PraisonAI's first-party A2A server example exposes an unauthenticated A2A JSON-RPC endpoint and registers a `calculate(expression)` tool implemented with Python `eval()`. The example also binds to `0.0.0.0`. A remote unauthenticated attacker can send `message/send` to `/a2a`; the request reaches `agent.chat()`, and a real LLM can invoke the registered `calculate` tool. In testing with `gemini/gemini-2.5-flash-lite`, this resulted in arbitrary Python execution in the server process, confirmed by creation of a marker file from an unauthenticated HTTP request. The issue affects deployments following the official A2A example or similar unauthenticated public A2A deployments with unsafe tools. The default unauthenticated A2A surface also exposes task history and task cancellation APIs, increasing confidentiality and integrity impact. Version 4.6.40 patches the issue.

Published Jul 21, 2026 · Updated Oct 15, 2026 · Sources: NIST National Vulnerability Database, CVE Program (cve.org) e CISA ADP · CNA: GitHub_M

Who exploits it and how urgent it is

A 0–100 score combining confirmed exploitation, ransomware and APT use, public exploits, EPSS and severity.

No exploitation signal in the sources consulted so far.
How the score was calculated
  • Technical severity (critical)+10
  • CISA SSVC: exploitation "poc"+5
  • Automatable exploitation (SSVC)+3

The score orders the patch queue; it does not replace your asset context (internet exposure, criticality, compensating controls).

Triage

Is it exploited, how likely is exploitation, what does it touch, and how severe do the sources call it.

Exploitation
Not confirmed
Not in CISA KEV — an absence of record, not proof it is unexploited.
EPSS FIRST
—
No EPSS score.
Affects
MervinPraison
PraisonAI
CVSS base
9.8
Critical · 2 source(s)

CISA SSVC assessment CISA

Three decision points CISA publishes for the CVEs it assesses (SSVC 2.0.3). A stakeholder decision, not a severity score.

Exploitation
Proof of concept
none · proof-of-concept · active
Automatable
Yes
can an attacker script the kill-chain steps
Technical impact
Total
partial · total control of the vulnerable component

Remediation

Fixes and mitigations documented by the sources — linked to the original advisory.

No fix documented by the sources we poll. That does not mean none exists: check the vendor advisory.

First 24 hours

Ordered from the record’s own fields — exposure first, because you cannot patch what you have not found. A rule-generated starting point.

  1. Identify exposed assets running the affected vendor/product/version combinations (MervinPraison PraisonAI).
  2. The attack is network-based and needs no privileges: restrict exposure (ACLs, VPN, WAF) until patched.
  3. No fix documented in the sources: reduce exposure and monitor the vendor advisory.
  4. Search available logs for exploit probes matching the vulnerability class (injection), errors and authentication anomalies.

Affected scope

Vendor, product and versions as the sources word them.

VendorProductVersionsStatusSource
MervinPraison PraisonAI version < 4.6.40 Vulnerable CVE Program (cve.org) e CISA ADP

Attack characteristics

The CVSS vector, decoded. It describes the attack, not your exposure to it.

Attack vector
Network
Attack complexity
Low
Privileges required
None
User interaction
None
Scope
Unchanged
Confidentiality
High
Integrity
High
Availability
High

Every base score collected

Sources score independently and may disagree; each row says who scored it and under which version.

ScoreVersionSeverityExpl.ImpactScored by
9.8 CVSS 3.1 Critical 3.9 5.9 security-advisories@github.com via NIST National Vulnerability Database
9.8 CVSS 3.1 Critical — — GitHub_M via CVE Program (cve.org) e CISA ADP
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H (score shown at the top: security-advisories@github.com)

Weakness MITRE

Weakness class according to MITRE’s CWE catalog.

CWE-95 · Eval Injection

Other CVEs with this weakness →

Detection

Read off the CVSS vector and the weakness class. Starting points, not tested rules.

  • Prioritize edge telemetry for the network-reachable component (proxy, WAF, IDS/IPS).
  • Look for parameters with command/query metacharacters and unexpected child processes of the service.
web/proxy/WAF logsnetwork IDS/IPSapplication logsendpoint telemetry (EDR)

Timeline

What happened to this CVE, newest first.

  • 2026
  • Affected products added · mervinpraison/praisonai
    Oct 15, 2026 · CVE Program (cve.org) e CISA ADP
  • SSVC assessment updated
    Oct 15, 2026 · CVE Program (cve.org) e CISA ADP
  • Record published
    Oct 15, 2026
  • CVSS changed · 9.8
    Oct 15, 2026 · NIST National Vulnerability Database
  • Source status changed · → Deferred
    Oct 15, 2026 · NIST National Vulnerability Database
  • Record created in this database
    Oct 15, 2026 · NIST National Vulnerability Database
  • CVE published
    Jul 21, 2026 · GitHub_M

Source activity

Repeated readings are counted rather than listed.

  • 1× Official description updated · Oct 15, 2026 – Oct 15, 2026

References

3 on the record

Elsewhere on this site

MervinPraison
every CVE for this vendor
Injection
same class
CWE-95
other pages naming this weakness

Related CVEs (same products)

  • CVE-2026-57118 PraisonAI AgentTeam.launch exposes unauthenticated remote agent listing and invocation endpoints 3d
  • CVE-2026-62176 PraisonAI: Code Injection via f-string Interpolation in Deploy API Server Generation 8d
  • CVE-2026-55539 PraisonAI: [Auth Bypass] PraisonAI async Jobs API (`/api/v1/runs`) has no authentication — unauthenticated job execution, result theft, cancel and delete Aug 25, 2026
  • CVE-2026-55533 PraisonAI: Authentication fail-open in Recipe server allows unauthenticated access when API key or JWT auth is configured without a secret Aug 25, 2026
  • CVE-2026-55531 PraisonAI: Unauthenticated unbounded session accumulation in the PraisonAI MCP HTTP server (memory exhaustion; session TTL never enforced) Aug 25, 2026
  • CVE-2026-55534 PraisonAI serve agents --api-key is ignored, allowing unauthenticated remote agent execution Aug 25, 2026

Not in any source we poll

Listed rather than left blank: an empty field and an unmeasured one look identical on screen, and only one is a reason to look elsewhere.

  • No FIRST EPSS score.
  • No fixed version, patch or mitigation documented.
  • No confirmed IOCs, IP addresses, domains, file hashes, or malware artifacts supplied.
  • No organization-specific asset inventory, compensating-control status, or patch deployment evidence supplied.
  • No exploit packet captures, log samples, or incident case IDs supplied.

Answered from this record

Text assembled only from the fields above — no additional claims.

What should defenders know first?

CVE-2026-47391 is "PraisonAI's unauthenticated A2A official example can reach real LLM-driven `eval()` tool execution", rated Critical. It affects PraisonAI (MervinPraison); versions are in the scope table. It is not in CISA KEV, which does not rule out exploitation. CVSS 9.8 describes technical severity. First verify whether exposed or business-critical assets run the affected versions, apply vendor fixes or mitigations, and preserve logs for review.

Comments

Moderated technical discussion. Read the community guidelines.

No comments yet.

Sign in or create an account to comment and suggest corrections.