CVE-2026-39889
PraisonAI has Unauthenticated SSE Event Stream Exposes All Agent Activity in A2U Server
PraisonAI is a multi-agent teams system. Prior to 4.5.115, the A2U (Agent-to-User) event stream server in PraisonAI exposes all agent activity without authentication. The create_a2u_routes() function registers the following endpoints with NO authentication checks: /a2u/info, /a2u/subscribe, /a2u/events/{stream_name}, /a2u/events/sub/{id}, and /a2u/health. This vulnerability is fixed in 4.5.115.
Attack profile
How easy it is to exploit
- Attack vector
- Network
- Complexity
- Low
- Privileges needed
- None
- User interaction
- None
What an attacker can affect
- Confidentiality
- High
- Integrity
- None
- Availability
- None
Exploit likelihood
What each source reports
CVE List Score used
7.5
PraisonAI has Unauthenticated SSE Event Stream Exposes All Agent Activity in A2U Server
PraisonAI is a multi-agent teams system. Prior to 4.5.115, the A2U (Agent-to-User) event stream server in PraisonAI exposes all agent activity without authentication. The create_a2u_routes() function registers the following endpoints with NO authentication checks: /a2u/info, /a2u/subscribe, /a2u/events/{stream_name}, /a2u/events/sub/{id}, and /a2u/health. This vulnerability is fixed in 4.5.115.
- Record
CVE-2026-39889- CVSS 3.1
- 7.5 High
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N - Weakness
- CWE-200
- Updated
- 2026-11-02
EUVDEUVD-2026-20636
7.5
PraisonAI is a multi-agent teams system. Prior to 4.5.115, the A2U (Agent-to-User) event stream server in PraisonAI exposes all agent activity without authentication. The create_a2u_routes() function registers the following endpoints with NO authentication checks: /a2u/info, /a2u/subscribe, /a2u/events/{stream_name}, /a2u/events/sub/{id}, and /a2u/health. This vulnerability is fixed in 4.5.115.
- Record
EUVD-2026-20636- CVSS 3.1
- 7.5 High
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N - Updated
- 2026-11-02
GitHub AdvisoriesGHSA-f292-66h9-fpmf
7.5
PraisonAI Has Unauthenticated SSE Event Stream that Exposes All Agent Activity in A2U Server
The A2U (Agent-to-User) event stream server in PraisonAI exposes all agent activity without authentication. This is a separate component from the gateway server fixed in CVE-2026-34952.
The create_a2u_routes() function registers the following endpoints with NO authentication checks:
- GET /a2u/info — exposes server info and stream names
- POST /a2u/subscribe — creates event stream subscription
- GET /a2u/events/{stream_name} — streams ALL agent events
- GET /a2u/events/sub/{id} — streams events for subscription
- GET /a2u/health — health check
An unauthenticated attacker can:
- POST /a2u/subscribe → receive subscription_id
- GET /a2u/events/sub/{subscription_id} → receive live SSE stream of all agent events including responses, tool calls, and thinking
This exposes sensitive agent activity including responses, internal reasoning, and tool call arguments to any network attacker.
<img width="1512" height="947" alt="image" src="https://github.com/user-attachments/assets/3438f3ea-75ec-4978-9dd9-d9a6da42c248" />
<img width="1512" height="571" alt="image" src="https://github.com/user-attachments/assets/ee3313f6-f522-48f7-9c06-e5e265c6aeb4" />
[1] POST /a2u/subscribe (no auth token) Status: 200 Response: {"subscription_id":"sub-a1ad8a6edd8b","stream_name":"events", "stream_url":"http://testserver/a2u/events/sub-a1ad8a6edd8b"} Got subscription_id: sub-a1ad8a6edd8b
[2] GET /a2u/info (no auth token) Status: 200 Response: {"name":"A2U Event Stream","version":"1.0.0", "streams":["events"],"event_types":["agent.started","agent.thinking", "agent.tool_call","agent.response","agent.completed","agent.error"]}
[3] GET /a2u/health (no auth token)
Status: 200
Response: {"status":"healthy","active_subscriptions":1,"active_streams":1}
Impact: Attacker can subscribe and receive ALL agent events including responses, tool calls, and internal reasoning in real-time
- Record
GHSA-f292-66h9-fpmf- CVSS 3.1
- 7.5 High
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N - Weakness
- CWE-200
- Updated
- 2026-11-02
NVD
7.5
PraisonAI is a multi-agent teams system. Prior to 4.5.115, the A2U (Agent-to-User) event stream server in PraisonAI exposes all agent activity without authentication. The create_a2u_routes() function registers the following endpoints with NO authentication checks: /a2u/info, /a2u/subscribe, /a2u/events/{stream_name}, /a2u/events/sub/{id}, and /a2u/health. This vulnerability is fixed in 4.5.115.
- Record
CVE-2026-39889- CVSS 3.1
- 7.5 High
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N - Weakness
- CWE-200
- Updated
- 2026-11-02
OSV
7.5
PraisonAI has Unauthenticated SSE Event Stream Exposes All Agent Activity in A2U Server
PraisonAI is a multi-agent teams system. Prior to 4.5.115, the A2U (Agent-to-User) event stream server in PraisonAI exposes all agent activity without authentication. The create_a2u_routes() function registers the following endpoints with NO authentication checks: /a2u/info, /a2u/subscribe, /a2u/events/{stream_name}, /a2u/events/sub/{id}, and /a2u/health. This vulnerability is fixed in 4.5.115.
- Record
CVE-2026-39889- CVSS 3.1
- 7.5 High
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N - Weakness
- CWE-200
- Updated
- 2026-11-02
OSVGHSA-f292-66h9-fpmf
7.5
PraisonAI Has Unauthenticated SSE Event Stream that Exposes All Agent Activity in A2U Server
The A2U (Agent-to-User) event stream server in PraisonAI exposes all agent activity without authentication. This is a separate component from the gateway server fixed in CVE-2026-34952.
The create_a2u_routes() function registers the following endpoints with NO authentication checks:
- GET /a2u/info — exposes server info and stream names
- POST /a2u/subscribe — creates event stream subscription
- GET /a2u/events/{stream_name} — streams ALL agent events
- GET /a2u/events/sub/{id} — streams events for subscription
- GET /a2u/health — health check
An unauthenticated attacker can:
- POST /a2u/subscribe → receive subscription_id
- GET /a2u/events/sub/{subscription_id} → receive live SSE stream of all agent events including responses, tool calls, and thinking
This exposes sensitive agent activity including responses, internal reasoning, and tool call arguments to any network attacker.
<img width="1512" height="947" alt="image" src="https://github.com/user-attachments/assets/3438f3ea-75ec-4978-9dd9-d9a6da42c248" />
<img width="1512" height="571" alt="image" src="https://github.com/user-attachments/assets/ee3313f6-f522-48f7-9c06-e5e265c6aeb4" />
[1] POST /a2u/subscribe (no auth token) Status: 200 Response: {"subscription_id":"sub-a1ad8a6edd8b","stream_name":"events", "stream_url":"http://testserver/a2u/events/sub-a1ad8a6edd8b"} Got subscription_id: sub-a1ad8a6edd8b
[2] GET /a2u/info (no auth token) Status: 200 Response: {"name":"A2U Event Stream","version":"1.0.0", "streams":["events"],"event_types":["agent.started","agent.thinking", "agent.tool_call","agent.response","agent.completed","agent.error"]}
[3] GET /a2u/health (no auth token)
Status: 200
Response: {"status":"healthy","active_subscriptions":1,"active_streams":1}
Impact: Attacker can subscribe and receive ALL agent events including responses, tool calls, and internal reasoning in real-time
- Record
GHSA-f292-66h9-fpmf- CVSS 3.1
- 7.5 High
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N - Weakness
- CWE-200
- Updated
- 2026-11-02
OSVPYSEC-2026-2911
7.5
PraisonAI Has Unauthenticated SSE Event Stream that Exposes All Agent Activity in A2U Server
The A2U (Agent-to-User) event stream server in PraisonAI exposes all agent activity without authentication. This is a separate component from the gateway server fixed in CVE-2026-34952.
The create_a2u_routes() function registers the following endpoints with NO authentication checks:
- GET /a2u/info — exposes server info and stream names
- POST /a2u/subscribe — creates event stream subscription
- GET /a2u/events/{stream_name} — streams ALL agent events
- GET /a2u/events/sub/{id} — streams events for subscription
- GET /a2u/health — health check
An unauthenticated attacker can:
- POST /a2u/subscribe → receive subscription_id
- GET /a2u/events/sub/{subscription_id} → receive live SSE stream of all agent events including responses, tool calls, and thinking
This exposes sensitive agent activity including responses, internal reasoning, and tool call arguments to any network attacker.
<img width="1512" height="947" alt="image" src="https://github.com/user-attachments/assets/3438f3ea-75ec-4978-9dd9-d9a6da42c248" />
<img width="1512" height="571" alt="image" src="https://github.com/user-attachments/assets/ee3313f6-f522-48f7-9c06-e5e265c6aeb4" />
[1] POST /a2u/subscribe (no auth token) Status: 200 Response: {"subscription_id":"sub-a1ad8a6edd8b","stream_name":"events", "stream_url":"http://testserver/a2u/events/sub-a1ad8a6edd8b"} Got subscription_id: sub-a1ad8a6edd8b
[2] GET /a2u/info (no auth token) Status: 200 Response: {"name":"A2U Event Stream","version":"1.0.0", "streams":["events"],"event_types":["agent.started","agent.thinking", "agent.tool_call","agent.response","agent.completed","agent.error"]}
[3] GET /a2u/health (no auth token)
Status: 200
Response: {"status":"healthy","active_subscriptions":1,"active_streams":1}
Impact: Attacker can subscribe and receive ALL agent events including responses, tool calls, and internal reasoning in real-time
- Record
PYSEC-2026-2911- CVSS 3.1
- 7.5 High
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N - Updated
- 2026-11-02
Affected products
Affected packages
| Package | Affected | Fixed |
|---|---|---|
praisonaiPyPI |
through 4.5.114 | 4.5.115 |
praisonaiPyPI |
before 4.5.115, plus listed versions 0.0.10.0.100.0.110.0.120.0.13 Show 45 moreShow less0.0.140.0.150.0.160.0.170.0.180.0.190.0.20.0.200.0.210.0.220.0.230.0.240.0.250.0.260.0.270.0.280.0.290.0.30.0.300.0.310.0.320.0.330.0.340.0.350.0.360.0.370.0.380.0.390.0.40.0.400.0.410.0.420.0.430.0.440.0.450.0.460.0.470.0.480.0.490.0.50.0.500.0.520.0.530.0.540.0.55 |
4.5.115 |
History
| Recorded | Changed | Sources |
|---|---|---|
| first indexed | CVE List, EUVD, GitHub Advisories, NVD, OSV |
Dates are when Every CVE recorded each change. Upstream dates may differ.
In short
CVE-2026-39889 is a high vulnerability (CVSS 7.5) in Mervinpraison Praisonai, published April 8, 2026. No source lists public exploit code. EPSS puts the chance of exploitation in the next 30 days at 0.43%, the 37th percentile. Fixed in praisonai 4.5.115.
References
github.com/MervinPraison/PraisonAI/security/advisories/GHSA-f292-66h9-fpmf
github.com/MervinPraison/PraisonAI/releases/tag/v4.5.115
nvd.nist.gov/vuln/detail/CVE-2026-39889
github.com/advisories/GHSA-f292-66h9-fpmf
github.com/CVEProject/cvelistV5/tree/main/cves/2026/39xxx/CVE-2026-39889.json
github.com/MervinPraison/PraisonAI
pypi.org/project/praisonai
Left out here: 623 versions. The JSON record has them.