Vulnerability · Published Sep 3, 2026 · Assigned by VulnCheck
CVE-2026-85093Cheshire Cat AI Memory Collection Endpoint Information Disclosure
Medium 6.5
In plain English
A medium-severity incorrect authorization in core from cheshire-cat-ai. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 0.4% (higher than 36% of all known vulnerabilities).
Severity (CVSS 3.1)6.5Medium
Exploit odds (30 days)0.4%top 64.0% of all CVEs
Exploited in the wildNo reportsCISA SSVC: poc
Attack toolingNoneno public tooling known
Official 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.
Affected products (as reported)
| Vendor | Product | Versions |
|---|---|---|
| cheshire-cat-ai | core | 1.8.0 – through 1.9.2 |
Weakness: CWE-863 · Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N
References
- GitHub Issue #1136 issue-tracking
- https://github.com/cheshire-cat-ai/core/blob/1.9.2/core/cat/routes/memory/points.py#L350 technical-description
- https://github.com/cheshire-cat-ai/core/blob/1.9.2/core/cat/looking_glass/stray_cat.py technical-description
- https://github.com/cheshire-cat-ai/core product
- VulnCheck Advisory: Cheshire Cat AI Memory Collection Endpoint Information Disclosure third-party-advisory