Machine-written summary
Summary written by Claude Haiku from the source advisory. Not reviewed by a person.
RAGAS versions from 0.2.3 up to but not including 0.3.0-rc1 are vulnerable to arbitrary file read through the ImageTextPromptValue class. The flaw is improper validation of URLs passed in the retrieved_contexts parameter when handling multimodal inputs, so an attacker who can supply those inputs may be able to read files on the system. Upgrade to ragas 0.3.0-rc1 or later. The source gives few details about the exact attack conditions.
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 |
|---|---|---|---|---|
| 7.5 | High | 3.1 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N | GitHub Advisory Database |
- CISA KEV Not listed.
- EPSS 0.0061, the 49th percentile, on 15 Nov 2026: FIRST’s estimate of the chance of exploitation in the next 30 days.
Timeline
- 31 Oct 2026, 15:01 UTC First seen by agentprime
- 31 Oct 2026, 15:01 UTC Confirmed by OSV
Sources
- GitHub Advisory Database: GHSA-v2xr-wvrv-p969
- OSV: GHSA-v2xr-wvrv-p969
- nvd.nist.gov/vuln/detail/CVE-2025-45691
- github.com/explodinggradients/ragas/pull/1559
- github.com/vibrantlabsai/ragas/pull/1991
- github.com/vibrantlabsai/ragas/commit/b28433709cbedbb531db79dadcfbdbd3aa6adcb0
- adithyanak.com/ragas-v0214-arbitrary-file-read-vulnerability
- github.com/explodinggradients/ragas/blob/e97886ac976465efb60e5949c5d69baf30cc811d/src/ragas/prompt/multi_modal_prompt.py#L202
- github.com/vibrantlabsai/ragas