Machine-written summary
Summary written by Claude Haiku from the source advisory. Not reviewed by a person.
PraisonAI's praisonaiagents package, versions before 4.5.128, exposes an AGUI endpoint (POST /agui) that has no authentication and sends a wildcard Access-Control-Allow-Origin header. A malicious website visited by a user running the AGUI server locally can trigger agent execution, including tool calls, and read the responses, which may expose file contents or other sensitive data. Upgrade praisonaiagents to version 4.5.128 or later; the source does not describe a workaround beyond not running the AGUI server while visiting untrusted sites.
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
| Score | Rating | CVSS | Vector | Source |
|---|---|---|---|---|
| 8.1 | High | 3.1 | CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:N | GitHub Advisory Database |
- CISA KEV Not listed.
- EPSS No score.
Timeline
- 31 Oct 2026, 14:11 UTC First seen by agentprime
- 31 Oct 2026, 14:11 UTC Confirmed by OSV