Ai Inference ServerApplication · Redhat
CVE-2025-6920
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 flaw was found in the authentication enforcement mechanism of a model inference API in ai-inference-server. All /v1/* endpoints are expected to enforce API key validation. However, the POST /invocations endpoint failed to do so, resulting in an authentication bypass. This vulnerability allows unauthorized users to access the same inference features available on protected endpoints, potentially exposing sensitive functionality or allowing unintended access to backend resources.
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 · high confidenceThe POST /invocations endpoint in ai-inference-server's model inference API lacks API key authentication enforcement, unlike other /v1/* endpoints. This allows unauthenticated attackers to bypass authentication and access protected inference functionality.
Verify against the referenced sources before acting — the references below are authoritative for this CVE, this summary is not.
Affected products & versions What the vendor confirmedThe version ranges the vendor confirmed as vulnerable. If your version sits inside a range here, treat yourself as exposed until you have upgraded.
NVD · CPE data
Ai Inference ServerApplication
all versionsCVSS 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
- None
- User interaction
- None
- Scope
- Unchanged
- Confidentiality
- Low
- Integrity
- None
- Availability
- None
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N
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.
-
Identify if ai-inference-server is deployedCheck for running processes: 'ps aux | grep ai-inference-server' or check container images: 'docker ps' if running in containersAffected if ai-inference-server from Red Hat is installed or running
-
Verify authentication is required on other /v1/* endpointsSend a request to a known protected endpoint like POST /v1/models/{model_name}/infer without an API key header and confirm it returns 401 UnauthorizedAffected if Other /v1/* endpoints properly enforce authentication (this establishes the baseline)
-
Test /invocations endpoint without authenticationSend a POST request to /invocations endpoint without an 'Authorization' or 'X-API-Key' header, using a valid inference payloadAffected if Request succeeds (200 OK) without requiring API key authentication - this indicates the vulnerability is present
-
Check API key configuration for /invocationsReview the ai-inference-server configuration files or deployment manifests for authentication settings specific to the /invocations routeAffected if No API key validation is configured for /invocations while other /v1/* routes have authentication settings
If the /invocations endpoint accepts requests without an API key while other /v1/* endpoints properly require authentication, the environment is affected by CVE-2025-6920.
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 proper API key validation on the POST /invocations endpoint to match the authentication enforcement present on other /v1/* endpoints.
Fix this in Ai Inference Server
Scoped from the published advisory
- Consultation3.0 h
- Implementation4.0 h
- Testing3.0 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 $3,408.
Scan for this in your stack
Free · runs locallyCheck whether your project pulls in CVE-2025-6920 — 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-2025-6920 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