CVE-2026-6587
Official description Straight from the sourceThe vendor's or NVD's own wording, published unedited. Authoritative, but often terse — it says what broke, rarely what to do.
NVD · uneditedA security flaw has been discovered in vibrantlabsai RAGAS up to 0.4.3. The affected element is the function _try_process_local_file/_try_process_url of the file src/ragas/metrics/collections/multi_modal_faithfulness/util.py of the component Collections Module. Performing a manipulation of the argument retrieved_contexts results in server-side request forgery. The attack can be initiated remotely. The exploit has been released to the public and may be used for attacks. The security patch for CVE-2025-45691 was applied to a different module only. The vendor was contacted early about this disclosure but did not respond in any way.
Technical summary Written by usOur analysis, written from the advisory, the CVSS vector and the affected-version data. It adds context the advisory leaves out, and never invents facts that are not in the source.
dbcve analysis · moderate confidenceThis is a Server-Side Request Forgery (SSRF) vulnerability in the RAGAS library's Collections Module. The affected functions _try_process_local_file and _try_process_url in src/ragas/metrics/collections/multi_modal_faithfulness/util.py do not properly validate the retrieved_contexts argument, allowing an attacker to manipulate the input to make the server request arbitrary internal or external URLs or access local files.
Verify against the referenced sources before acting — the references below are authoritative for this CVE, this summary is not.
CVSS breakdown How the score is builtThe industry scoring standard. It rates how the flaw is reached, what it takes to exploit, and what an attacker gains — the score is derived from those, not the other way round.
From the vector- Attack vector
- Network
- Complexity
- Low
- Privileges
- Low
- User interaction
- None
- Scope
- Unchanged
- Confidentiality
- Low
- Integrity
- Low
- Availability
- Low
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:L/A:L
Am I affected? How to checkSteps we derive from the advisory and the affected-version data, so you can decide whether this CVE reaches your setup. They are a guide, not a scan — your own configuration is the authority.
dbcve checksWork through these to decide whether this CVE applies to you.
-
Verify RAGAS library installationRun 'pip show ragas' or check your project's dependency list to confirm RAGAS is installed and note its versionAffected if RAGAS library is present in the environment and version is any release containing the affected code (src/ragas/metrics/collections/multi_modal_faithfulness/util.py)
-
Locate the affected source fileCheck for the presence of src/ragas/metrics/collections/multi_moda_faithfulness/util.py in your RAGAS installation directory (typically in site-packages or project vendor folder)Affected if The file exists and contains the vulnerable _try_process_local_file and _try_process_url functions
-
Examine function signatures for retrieved_contexts parameterOpen the affected file and inspect the _try_process_local_file and _try_process_url function definitions for how they handle the retrieved_contexts argumentAffected if The functions accept retrieved_contexts without strict validation (no allowlisting of URLs, schemes, or file paths)
-
Check input validation logicSearch the affected file for any validation logic that sanitizes or validates retrieved_contexts before processing (look for allowlists, blocklists, regex patterns, or URL/file path checks)Affected if No input validation is found, or validation is weak/absent on the retrieved_contexts parameter passed to these functions
You are affected if the RAGAS library is installed and your application or workflow passes untrusted or user-controlled retrieved_contexts input to the _try_process_local_file or _try_process_url functions without prior validation.
Generated from the published advisory. Verify against your own configuration.
Remediation Closing itWhat it takes to close this. Where a vendor fix exists we point at it; where none exists we say so plainly, and can build one. Effort estimates are scoped from the advisory, not from your codebase.
From vendor dataImplement strict input validation on the retrieved_contexts parameter before passing it to _try_process_local_file/_try_process_url functions. Use allowlists for permitted URL schemes, domains, and file paths. Apply network segmentation to limit the impact of any SSRF exploitation.
- Consultation3.0 h
- Implementation8.0 h
- Testing4.0 h
- Review / QA2.0 h
An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $4,800.
Scan for this in your stack
Free · runs locallyCheck whether your project pulls in CVE-2026-6587 — or any other known-vulnerable package — straight from your lock files. Free and open source; it runs locally and uploads nothing.
References Go to the primary sourcePrimary sources — vendor advisories, patches and trackers. Where our summary and a reference disagree, the reference wins.
Primary sourcesPractitioner notes
ContributedPeer-ranked notes from engineers who’ve handled CVE-2026-6587 in production — separate from our analysis above.
The advisory tells you what broke. It rarely tells you what actually worked. If you’ve dealt with this one, that detail is what the next engineer is searching for.
- The version that genuinely resolved it — not the one the vendor claimed
- A config change or rule that shut the vector down
- A gotcha in the upgrade path that cost you an afternoon
No notes yet
Be the first to add a field note for this CVE — a mitigation you’ve verified, a version caveat, or a link to a working fix. Sign in above to contribute.
A place for practitioners to share what actually worked: a mitigation you’ve tested, a configuration change, a version- or environment-specific caveat, or a link to a verified patch. The most useful notes rise to the top as peers upvote them, so the signal stays high.
- Verified mitigations, workarounds, and config changes
- Version or environment caveats, and links to real fixes
- No weaponised exploit code, or anything meant to cause harm
- No spam, self-promotion, credentials, or personal data