Your RSA-2048 keys break in 2030. Find every one of them before attackers do.
🐍
🐍 PyPI
Not in CISA KEV
CRITICAL severity

CVE-2026-47391

CRITICALFix: MervinPraison/PraisonAI@e0fb8e7

CVE-2026-47391 is a critical-severity (CVSS 9.8) CWE-95 vulnerability in praisonai. O3 Security confirms whether CVE-2026-47391 is actually reachable in your code before you act, and blocks exploitation at runtime until you patch.

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

Also known asGHSA-vg22-4gmj-prxwPYSEC-2026-478
Published
Jul 21, 2026
Updated
Aug 12, 2026
Affected
1 pkg
Patched
1 / 1
Exploits
None indexed
Exploitation data as of Aug 15, 2026 · OSV.dev, NVD, FIRST.org (EPSS)

Exploitation Status

Proof-of-concept exploit code exists

  • CISA’s SSVC triage found public proof-of-concept exploit code for this CVE, though no confirmed active exploitation.
  • CISA assesses this as automatable — exploitation doesn’t require manual, per-target effort, which raises the odds of mass scanning and opportunistic attacks.
  • A successful exploit gives an attacker total control of the affected component, not partial access.

Exploitation and automatability from CISA’s SSVC triage for CVE-2026-47391.

EPSS Exploitation Probability

via FIRST.org ↗
0.8%probability of exploitation in next 30 days
Lower Risk0.00%
Lower risk than most CVEs53th percentile — riskier than 53% of all scored CVEsHighest risk
0.28%0.61%0.95%1.28%0.8%0.8%Aug 26Aug 26

EPSS (Exploit Prediction Scoring System) is a daily probability model maintained by FIRST.org. It estimates the likelihood a CVE will be exploited in production environments within the next 30 days, derived from real-world threat intelligence signals.

How urgent is this, really

CVE-2026-47391 plotted by exploitation likelihood (EPSS) against impact (CVSS). The shaded corner — EPSS 50%+ and CVSS 7.0+ — is where this CVE doesn't sit, though severity or exploitability alone can still warrant action.

Where this sits among everything scored

Of 365,017 CVEs with a current EPSS score, this one falls in the < 10% band (highlighted). Real counts from FIRST.org, not a sample — log-scaled since the landscape is heavily right-skewed.

Real-World Exposure

1 pkg affected
🐍praisonai

Real-time download stats are indexed for npm and PyPI packages. This vulnerability affects PyPI packages — download data is not available via public APIs for these ecosystems.

Description

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.

Affected Packages

1 total 1 fixed
EcosystemPackageVulnerable rangeFix
🐍PyPIpraisonaiall versions4.6.40

Detection & mitigation playbook

Open-source dependency
  1. Detect

    Scan your dependency tree (package-lock.json, pnpm-lock.yaml, requirements.txt, go.sum, etc.) for praisonai. O3's reachability analysis confirms whether the vulnerable code path is actually invoked in your application, so you act on real exposure instead of every transitive match.

  2. Fix

    Update praisonai to 4.6.40 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms CVE-2026-47391 is resolved across your whole dependency graph.

  3. Workarounds

    If you can't upgrade right away: gate or disable the affected feature, validate untrusted input at the boundary, and avoid passing attacker-controlled data into the vulnerable path. O3's runtime protection blocks exploitation in production as an interim safeguard until the upgrade lands.

  4. How O3 protects you

    O3 pinpoints whether CVE-2026-47391 is reachable in your code and exactly where to fix it, then blocks exploitation in production at runtime until the patched version is deployed.

Tailored to CVE-2026-47391. Runtime protection reduces exposure until a permanent patch is applied and verified — it complements patching, it doesn't replace it.

Frequently Asked Questions

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
O3 Security · Impact-Aware SCA

Is CVE-2026-47391 in your dependencies?

O3 detects CVE-2026-47391 across PyPI dependencies and uses function-level reachability to confirm whether the vulnerable code path is actually reachable — not just present. No false positives.

CVE-2026-47391: praisonai (Critical 9.8) | O3 Security