Machine-written summary
Summary written by Claude Haiku from the source advisory. Not reviewed by a person.
PraisonAI (PyPI package praisonai) versions before 4.5.128 have a flaw in the AST-based Python sandbox used by the python tools, which can be bypassed by calling type.__getattribute__ to resolve blocked attributes dynamically. An attacker who can get untrusted agent code run by the sandbox can escape it and execute arbitrary code with the privileges of the host process. Upgrade praisonai to version 4.5.128 or later.
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 |
|---|---|---|---|---|
| 8.6 | High | 3.1 | CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H | CNA (GitHub_M) |
- CISA KEV Not listed.
- EPSS 0.0024, the 15th percentile, on 10 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.
Timeline
- 31 Oct 2026, 15:02 UTC First seen by agentprime
- 31 Oct 2026, 15:02 UTC Confirmed by OSV