Machine-written summary
Summary written by Claude Haiku from the source advisory. Not reviewed by a person.
The llama-index-core PyPI package is vulnerable in versions before 0.10.24, through a flaw in the safe_eval function of its exec_utils class that allows prompt injection to lead to arbitrary code execution. An attacker who can supply crafted prompt input can bypass method restrictions that were meant to block unauthorized code, which the source says bypasses the earlier CVE-2023-39662 fix. Upgrade llama-index-core to version 0.10.24 or later, which is listed as the fixed version.
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 0.0096, the 62nd percentile, on 16 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.
Timeline
- 31 Oct 2026, 14:07 UTC First seen by agentprime
- 31 Oct 2026, 14:07 UTC Confirmed by OSV
Sources
- GitHub Advisory Database: GHSA-wvpx-g427-q9wc
- OSV: GHSA-wvpx-g427-q9wc
- nvd.nist.gov/vuln/detail/CVE-2024-3098
- github.com/run-llama/llama_index/commit/2c92e88838a5f481d50840240b1dd3180066c6f5
- github.com/run-llama/llama_index/commit/5fbcb5a8b9f20f81b791c7fc8849e352613ab475
- github.com/pypa/advisory-database/tree/main/vulns/llama-index-core/PYSEC-2026-397.yaml
- github.com/run-llama/llama_index
- huntr.com/bounties/1bce0d61-ad03-4b22-bc32-8f99f92974e7
- pypi.org/project/llama-index-core