VulnerabilityPublished 10 Nov 2026

CVE-2026-108167: auth0-ai-langchain · Incorrect Authorization

Affects auth0-ai-langchainSource CVE Database V5

Compare

Not known to be exploited : upgrade to 1.0.2 soon.

Data as of 10 Nov 2026, 21:21 UTC

Severity

High

Rated High by Threat Radar's AI analysis · CVSS not yet scored by NVD

Thin evidence

One scorer or none

Patch: Available – fixed in 1.0.2, 1.0.3

Exploitation evidence

Disclosed: evidence found.
CVE published 10 Nov 2026
Detectable: no evidence on record.
No public nuclei template indexed
Weaponized: no evidence on record.
No public exploit code indexed in Metasploit or Exploit-DB
Exploited in the wildExploited: no evidence on record.
Not in CISA KEV and no source reports exploitation
Observed by OffSeq MirageSeen by Mirage: no evidence on record.
No attack traffic recorded by OffSeq Mirage sensors

A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 10 Nov 2026.

Disclosed: The CVE record is public on cve.org. Its publication is t = 0.
Detectable: A public nuclei template can find exposed instances, for defenders and attackers alike.
Weaponized: A Metasploit exploit module or Exploit-DB entry exists (Metasploit scanner modules do not count), or CISA SSVC or the CVSS exploit maturity reports a public proof of concept.
Exploited in the wild: CISA KEV lists it, CISA SSVC rates exploitation active, or a source reports attacks.
Observed by OffSeq Mirage: OffSeq Mirage honeypot sensors recorded attack traffic for this CVE, or found exposed hosts without attack traffic.

Moments are spaced evenly, not to scale; a dashed line marks a gap of six months or more. Deltas count from t = 0. Sources that give only a date (CISA KEV, Exploit-DB, or a time of exactly 00:00Z) read “same day” rather than hours. Metasploit modules carry the flaw’s disclosure date, not their release date, and nuclei templates carry no date, so both appear above but not on the timeline.

What to do

Upgrade auth0-ai-langchain to 1.0.2; auth0-ai-llamaindex to 1.0.3.

Affected software

Product	Affected	Fixed in
Auth0auth0-ai-langchain	Affected <1.0.2	Fixed in 1.0.2
Auth0auth0-ai-llamaindex	Affected <1.0.3	Fixed in 1.0.3
PyPIauth0-ai-langchain`pkg:pypi/auth0-ai-langchain`Other threats	Affected <1.0.2	Fixed in 1.0.2
PyPIauth0-ai-llamaindex`pkg:pypi/auth0-ai-llamaindex`Other threats	Affected <1.0.3	Fixed in 1.0.3

Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.

AI-suggested

Upgrade to auth0-ai-langchain versions 1.0.2 or 1.0.3, which contain fixes for this authorization issue. No other mitigation is indicated or required.

Description

CVE-2026-108167 is an authorization vulnerability in the auth0-ai-python FGA retriever component of Auth0's auth0-ai-langchain product. The flaw causes the retriever to fail to properly distinguish authorization checks across different users, relations, or conditions when filtering documents during retrieval-augmented generation. As a result, documents that should be denied by Auth0 FGA policies may be included in the model context and used in generated responses. Fixed versions 1.0.2 and 1.0.3 address this issue.

Impact

Unauthorized documents that should be denied by Auth0 FGA policies may be included in the model context and subsequently used in generated responses. This could lead to information disclosure or leakage of sensitive data that should have been restricted according to authorization policies.

Summary

The auth0-ai-python FGA retriever in Auth0's auth0-ai-langchain product does not correctly enforce authorization boundaries during document filtering in retrieval-augmented generation. Specifically, it does not differentiate authorization checks for different users, relations, or conditions, leading to unauthorized documents being included in the model context. This is classified as CWE-863 (Incorrect Authorization). The vulnerability affects versions prior to 1.0.2 and 1.0.3, which contain fixes.

CWE-863Incorrect Authorization (opens in a new tab)
Class weaknessLikelihood of exploit: HighCWE Top 25 (2025): #17OWASP Top 10 A01:2025: Broken Access Control (opens in a new tab)
The product performs an authorization check when an actor attempts to access a resource or perform an action, but it does not correctly perform the check.
Architecture and Design
Divide the product into anonymous, normal, privileged, and administrative areas. Reduce the attack surface by carefully mapping roles with data and functionality. Use role-based access control (RBAC) to enforce the roles at the appropriate boundaries.
Architecture and Design
Ensure that access control checks are performed related to the business logic. These checks may be different than the access control checks that are applied to more generic resources such as files, connections, processes, memory, and database records.
Architecture and Design · Libraries or Frameworks
Use a vetted library or framework that does not allow this weakness to occur or provides constructs that make this weakness easier to avoid.
OWASP Cheat Sheets
Authorization (opens in a new tab)
OWASP ASVS 4.0.3
V8.3.8 (opens in a new tab)
V13.4.2 (opens in a new tab)
V7.2.2 (opens in a new tab)
From MITRE CWE, MITRE CAPEC and OWASP (Top 10, OpenCRE).

References

trust.okta.com/security-advisories/improper-access-control-in-auth0-ai-python-document-retrieval-cve-2026-108167 (opens in a new tab)

Community reviews

Loading reviews…

Exploitation evidence

What to do

Affected software

Description

AI analysisMachine-generated, updated 10 Nov 2026, 21:21 UTC

WeaknessesCWE-863

Technical details

References

Community reviews

Related threats