Vulnerability · Published Oct 20, 2026 · Assigned by VulnCheck
CVE-2026-77938Letta through 0.16.8 Credential Exposure via Tool Sandbox Environment Inheritance
Medium 6.5
In plain English
A medium-severity security flaw in letta from letta-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 63.9% of all CVEs
Exploited in the wildNo reportsCISA SSVC: poc
Attack toolingNoneno public tooling known
Official description
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/run or custom tools to read LETTA_PG_URI, POSTGRES_PASSWORD, and provider API keys, then access cross-tenant database data.
Affected products (as reported)
Weakness: CWE-526 · Vector: CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N
References
- Lasso.security Advisory technical-description, exploit
- https://github.com/letta-ai/letta/blob/1131535716e8a31c9a437f8695e25ac98f203a24/letta/services/tool_sandbox/base.py#L487 technical-description
- VulnCheck Advisory: Letta through 0.16.8 Credential Exposure via Tool Sandbox Environment Inheritance third-party-advisory