Machine-written summary
Summary written by Claude Haiku from the source advisory. Not reviewed by a person.
The PraisonAI package (versions before 4.5.128) has its Chainlit UI hardcoded to auto-approve tool actions, overriding the administrator's PRAISON_APPROVAL_MODE setting, so shell commands run without an approval prompt. An authenticated user, including someone using default credentials, can get the agent to run single shell commands on the server with the permissions of the PraisonAI process. Upgrade to PraisonAI 4.5.128 or later. The source gives no workaround other than upgrading.
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 |
|---|---|---|---|---|
| 8.7 | High | 4.0 | CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N | CNA (VulnCheck) |
- CISA KEV Not listed.
- EPSS 0.0060, the 49th percentile, on 18 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.
Timeline
- 18 Jun 2026, 22:12 UTC Confirmed by the CVE List
- 31 Oct 2026, 15:05 UTC First seen by agentprime
- 31 Oct 2026, 15:05 UTC Confirmed by OSV