CVE-2026-108167
Auth0 AI Python retriever leaks unauthorized docs into RAG responses.
- CWE-863
- Authentication, Authorization, and Session Management
- Remote
The auth0-ai-python FGA retriever does not distinguish between authorization checks under different users, relations, or conditions when filtering documents during retrieval-augmented generation, resulting in documents denied by Auth0 FGA being included in the model context and used in the generated response.
- CWE
- CWE-863
- Published
- 2026-11-10
- OWASP
- A01 Broken Access Control
- Orthogonal defect classification
- Checking
- Code defect classification
- Missing Check
- Category
- Authentication, Authorization, and Session Management
- Subcategory
- Privilege Escalation
- Accessibility scope
- Remote
- Impact
- Information Disclosure
- Affected component
- auth0-ai-python
- Fixed by upgrading
- Yes
Solution
Upgrade to auth0‑ai‑python ≥ 0.2.3, which adds per‑user, relation, and condition enforcement in the FGA retriever to prevent unauthorized documents from being included in the RAG context.
Vulnerable code sample
import auth0_fga
from typing import List, Dict
class FGARetriever:
def __init__(self, fga_client: auth0_fga.FGAClient):
self.fga = fga_client
def retrieve_documents(self, query: str) -> List[Dict]:
# VULNERABLE: does not enforce per‑user authorization when filtering documents
allowed = self.fga.check("document:*", "read")
docs = self._search_index(query)
return [doc for doc in docs if doc["id"] in allowed]
def _search_index(self, query: str) -> List[Dict]:
# placeholder for search backend
return []Patched code sample
import auth0_fga
from typing import List, Dict
class FGARetriever:
def __init__(self, fga_client: auth0_fga.FGAClient):
self.fga = fga_client
def retrieve_documents(self, query: str, user_id: str) -> List[Dict]:
# FIX: enforce authorization checks for the specific user
allowed = self.fga.check(f"user:{user_id}", "document:*", "read")
docs = self._search_index(query)
return [doc for doc in docs if doc["id"] in allowed]
def _search_index(self, query: str) -> List[Dict]:
# placeholder for search backend
return []Cite this entry
@misc{vaitp:cve2026108167,
title = {{Auth0 AI Python retriever leaks unauthorized docs into RAG responses.}},
author = {Bogaerts, Fr\'ed\'eric and Ivaki, Naghmeh and Fonseca, Jos\'e},
year = {2026},
note = {VAITP Python Vulnerability Dataset, entry CVE-2026-108167},
howpublished = {\url{https://netpack.pt/vaitp/vulnerability/CVE-2026-108167/}}
}
Introducing the "VAITP dataset": a specialized repository of Python vulnerabilities and patches, meticulously compiled for the use of the security research community. As Python's prominence grows, understanding and addressing potential security vulnerabilities become crucial. Crafted by and for the cybersecurity community, this dataset offers a valuable resource for researchers, analysts, and developers to analyze and mitigate the security risks associated with Python. Through the comprehensive exploration of vulnerabilities and corresponding patches, the VAITP dataset fosters a safer and more resilient Python ecosystem, encouraging collaborative advancements in programming security.
The supreme art of war is to subdue the enemy without fighting.
Sun Tzu – “The Art of War”
:: Shaping the future through research and ingenuity ::
