Vulnpedia
← All CVEs

CVE-2026-47391

CRITICAL 9.8

Published 2026-07-21 · Last modified 2026-07-21

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.

ELEVATED IMPACT

Severe if exploited (CVSS 9.8), but no known exploitation and low modeled probability. Patch on a normal cadence.

Exploitation likelihood

—EPSS not yet scored

○ In CISA KEV ○ Public exploit / PoC

Impact if exploited

9.8CVSS 3.1 · CRITICAL

  • ConfidentialityHigh
  • IntegrityHigh
  • AvailabilityHigh

What an attacker needs

  • ✓Access: Reachable over the network — no local access needed
  • ✓Privileges: No account or privileges required
  • ✓User interaction: No user interaction needed
  • ✓Complexity: No special conditions — reliably repeatable

✓ lowers the bar for an attacker · ⚠ raises it

Proof of concept & exploit code

Test against your own equipment

curl -s https://vulnpedia.com/cve/CVE-2026-47391/poc.jsonMachine-readable PoC index for this CVE (for automation).

Listed for defensive triage, patch verification, and authorized testing on systems you own. Machine-readable: /cve/CVE-2026-47391/poc.json

Affected

Vendors Mervinpraison

Products Praisonai

Weakness (CWE)

  • CWE-95: : Improper Neutralization of Directives in Dynamically Evaluated Code ('Eval Injection')
  • CWE-306: : Missing Authentication for Critical Function

CVSS vector

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

All CVSS metrics

  • CRITICAL 9.8 v3.1 · CNA Primary
    CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
  • CRITICAL 9.8 v3.1 · NVD Secondary
    CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H

References

Technical & other

Sources: NVD · CVE.org · EPSS