Machine-written summary
Summary written by Claude Haiku from the source advisory. Not reviewed by a person.
The vanna package, versions up to and including 0.6.2, is vulnerable to remote code execution through prompt injection in its ask function. The source describes that the code the library generates from LLM output is run without a sandbox, so an attacker who can craft prompts can cause arbitrary code to run on the application's backend server. No fixed version is listed.
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 |
|---|---|---|---|---|
| 9.8 | Critical | 3.0 | CVSS:3.0/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H | CNA (@huntr_ai) |
- CISA KEV Not listed.
- EPSS 0.0088, the 59th percentile, on 14 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.