Unauthenticated code execution via unsafe type annotation evaluation
Published Mar 27, 2026 · Updated Mar 27, 2026
Code injection in Letta 0.16.4 allows remote attackers to execute operating-system commands through crafted tool annotations. The resolve_type function falls back to eval with Python built-ins when process_tool_arguments enables unsafe evaluation, causing an annotation expression to execute during argument coercion. A reachable self-hosted API that accepts and runs attacker-defined tools is required; successful exploitation compromises the server process.
Summary
What happened
Code injection in Letta 0.16.4 allows remote attackers to execute operating-system commands through crafted tool annotations. The resolve_type function falls back to eval with Python built-ins when process_tool_arguments enables unsafe evaluation, causing an annotation expression to execute during argument coercion. A reachable self-hosted API that accepts and runs attacker-defined tools is required; successful exploitation compromises the server process.
The record
- CVE
- CVE-2026-4965
- Published
- Mar 27, 2026
- Updated
- Mar 27, 2026
- Vendor
- Letta
- Product
- Letta
- Classifications
- CWE-95, CWE-94, T1190
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Mar 27, 2026CVE publishedPublication date reported by the CVE source.
- Mar 27, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=0.16.4
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
- YLChen-007 Letta type-annotation RCE proof of conceptfunctional · demonstrated
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo