# PraisonAI Has Unauthenticated SSE Event Stream that Exposes All Agent Activity in A2U Server

Advisory record · `GHSA-f292-66h9-fpmf`

- **Identifiers:** `GHSA-f292-66h9-fpmf` · `CVE-2026-39889` · `PYSEC-2026-2911`
- **State:** Confirmed
- **Severity:** CVSS 7.5 High
- **Critical:** No
- **Weakness (CWE):** [CWE-200](https://cwe.mitre.org/data/definitions/200.html)
- **Tags:** [Information disclosure](https://agentprime.io/advisories/tag/info-disclosure.md)
- **Published:** 8 Apr 2026
- **Updated:** 13 Jul 2026
- **Reviewed by a person:** No

Published by the GitHub Advisory Database at 8 Apr 2026, 19:21 UTC. agentprime has not analysed this yet, so whether it affects any app is not known.

## Affected packages

- `praisonai` (PyPI): affected `<4.5.115`; fixed in `4.5.115`

## Machine-written summary

Summary written by Claude Haiku from the source advisory. Not reviewed by a person.

> The PraisonAI package (PyPI praisonai) versions before 4.5.115 expose an A2U event stream server whose endpoints have no authentication checks. A remote attacker with network access can create a subscription and then receive a live stream of all agent events, including responses, tool call arguments, and internal reasoning. Upgrade to praisonai 4.5.115 or later. The source does not list a workaround.

Written 6 Nov 2026.

## Not analysed yet

We haven’t published our analysis of this Advisory yet. Once a person has reviewed it, this page will say what’s vulnerable, what has to be true for your app to be affected, and how to check.

## Severity and exploitation

- 7.5 High, CVSS 3.1: `CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N`, from CNA (GitHub_M)

- **CISA KEV:** Not listed.
- **EPSS:** 0.0043, the 38th percentile, on 16 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.

## Timeline

- 31 Oct 2026, 15:01 UTC: First seen by agentprime
- 31 Oct 2026, 15:01 UTC: [Confirmed by OSV](https://osv.dev/vulnerability/GHSA-f292-66h9-fpmf)

## Sources

- [GitHub Advisory Database: GHSA-f292-66h9-fpmf](https://github.com/advisories/GHSA-f292-66h9-fpmf)
- [OSV: GHSA-f292-66h9-fpmf](https://osv.dev/vulnerability/GHSA-f292-66h9-fpmf)
- <https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-f292-66h9-fpmf>
- <https://nvd.nist.gov/vuln/detail/CVE-2026-39889>
- <https://github.com/MervinPraison/PraisonAI>
- <https://github.com/MervinPraison/PraisonAI/releases/tag/v4.5.115>

Facts on this page come from the GitHub Advisory Database (CC-BY 4.0), OSV and the other sources listed, as published. We don’t reproduce full advisory descriptions, which can contain exploit code.

## Check whether this affects you

A Match means an installed version is in the affected range above. Most don’t affect the app; agentprime hasn’t analysed this one yet.

- With the agentprime MCP server (<https://api.agentprime.io/mcp>), ask your agent to check the project: `check_lockfile` sends a lockfile, `check_packages` a list of installed packages, and both return the Matches and the upgrades that clear them. `get_advisory` returns this record. Setup: <https://agentprime.io/mcp.md>
- In a browser: <https://agentprime.io/check/> reads your lockfile in the browser, never uploading it.
- Whether it touches your code, with file and line: the Claude Code plugin, <https://agentprime.io/plugin.md>
- As JSON: <https://api.agentprime.io/v1/advisories/GHSA-f292-66h9-fpmf>, or `POST https://api.agentprime.io/v1/match` with your packages (<https://agentprime.io/api.md>)

---

The web page: <https://agentprime.io/advisories/GHSA-f292-66h9-fpmf/>. Everything for agents: <https://agentprime.io/llms.txt>.
