letta-ai has 3 CVEs on record. 3 were published in the last 90 days. The busiest recent month was October 2026 with 3. The median CVSS is 8.1 (high), with 1 rated critical.
CVEs per month
Last 12 months, by publish date
- Exploited share
- 0% vs 1% corpus
- Median CVSS
- 8.1
- Publish → KEV
- —
- Last 90 days
- 3 prev 0
Weakness classes
Products
- letta 3
Worst active — by depth score
CVE-2026-77936Critical· 9.8Letta through 0.16.8 Insecure Default Configuration Unauthenticated API and PostgreSQL Access54CVE-2026-77937High· 8.1Letta through 0.16.8 Cross-Tenant Impersonation via user_id Header45CVE-2026-77938Medium· 6.5Letta through 0.16.8 Credential Exposure via Tool Sandbox Environment Inheritance36
letta-ai vulnerabilities
CVEs affecting letta-ai, newest first. Open any entry for full detail, references, and exploit status.
3 CVEsRSS
CVE-2026-77937High· 8.1Letta through 0.16.8 Cross-Tenant Impersonation via user_id Header
Letta through 0.16.8 contains an authentication bypass vulnerability that allows API callers to impersonate other users by supplying a self-asserted user_id HTTP header. Attackers can set user_id to another tenant's ID, even with LETTA_S…
CVE-2026-77938Medium· 6.5Letta through 0.16.8 Credential Exposure via Tool Sandbox Environment Inheritance
Letta through 0.16.8 contains an information disclosure vulnerability that allows users running tools to read server secrets because LocalSandbox subprocesses inherit the full server environment. Attackers can run code via POST /v1/tools…
CVE-2026-77936Critical· 9.8Letta through 0.16.8 Insecure Default Configuration Unauthenticated API and PostgreSQL Access
Letta through 0.16.8 ships a compose.yaml that does not enable LETTA_SERVER_SECURE, so the password middleware is never added and all API routes are unauthenticated, and it exposes a superuser PostgreSQL port with default credentials. Re…