VulnerabilityPublished 16 Jun 2025Updated 17 Jun 2025

CVE-2025-6101: letta · Eval Injection

Affects lettaSource CVE Database V5

Public exploit available · CVSS 5.1 Medium.

Data as of 26 Oct 2026, 10:12 UTC

CVSS 4.0 base score

5.1Medium

How severe the flaw is on the 0–10 CVSS scale.

EPSS: 0.3% chance of exploitation in 30 days – higher than 22% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.

CVSS:4.0/AV:A/AC:L/AT:N/PR:L/UI:N/VC:L/VI:L/VA:L/SC:N/SI:N/SA:N/E:P

Base metrics

Attack Vector: Adjacent
Attack Complexity: Low
Attack Requirements: None
Privileges Required: Low
User Interaction: None
Vulnerable system confidentiality: Low
Vulnerable system integrity: Low
Vulnerable system availability: Low
Subsequent system confidentiality: None
Subsequent system integrity: None
Subsequent system availability: None

Threat metrics

Exploit Maturity: POC

Bold values are the worst case: easiest to exploit or largest impact.

Attack Vector: Adjacent: The vulnerable system is bound to a protocol stack, but the attack is limited at the protocol level to a logically adjacent topology. This can mean an attack must be launched from the same shared proximity (e.g., Bluetooth, NFC, or IEEE 802.11) or logical network (e.g., local IP subnet), or from within a secure or otherwise limited administrative domain (e.g., MPLS, secure VPN within an administrative network zone).
Attack Complexity: Low: The attacker must take no measurable action to exploit the vulnerability. The attack requires no target-specific circumvention to exploit the vulnerability. An attacker can expect repeatable success against the vulnerable system.
Attack Requirements: None: The successful attack does not depend on the deployment and execution conditions of the vulnerable system. The attacker can expect to be able to reach the vulnerability and execute the exploit under all or most instances of the vulnerability.
Privileges Required: Low: The attacker requires privileges that provide basic capabilities that are typically limited to settings and resources owned by a single low-privileged user. Alternatively, an attacker with Low privileges has the ability to access only non-sensitive resources.
User Interaction: None: The vulnerable system can be exploited without interaction from any human user, other than the attacker.
Vulnerable system confidentiality: Low: There is some loss of confidentiality. Access to some restricted information is obtained, but the attacker does not have control over what information is obtained, or the amount or kind of loss is limited. The information disclosure does not cause a direct, serious loss to the Vulnerable System.
Vulnerable system integrity: Low: Modification of data is possible, but the attacker does not have control over the consequence of a modification, or the amount of modification is limited. The data modification does not have a direct, serious impact to the Vulnerable System.
Vulnerable system availability: Low: Performance is reduced or there are interruptions in resource availability. Even if repeated exploitation of the vulnerability is possible, the attacker does not have the ability to completely deny service to legitimate users. The resources in the Vulnerable System are either partially available all of the time, or fully available only some of the time, but overall there is no direct, serious consequence to the Vulnerable System.
Subsequent system confidentiality: None: There is no loss of confidentiality within the Subsequent System or all confidentiality impact is constrained to the Vulnerable System.
Subsequent system integrity: None: There is no loss of integrity within the Subsequent System or all integrity impact is constrained to the Vulnerable System.
Subsequent system availability: None: There is no impact to availability within the Subsequent System or all availability impact is constrained to the Vulnerable System.
Exploit Maturity: POC: Based on threat intelligence sources each of the following must apply: · Proof-of-concept is publicly available · No knowledge of reported attempts to exploit this vulnerability · No knowledge of publicly available solutions used to simplify attempts to exploit the vulnerability

Definitions: FIRST CVSS v4.0 specification.

Exploitation evidence

Disclosed: evidence found.
CVE published 16 Jun 2025
Detectable: no evidence on record.
No public nuclei template indexed
Weaponised: evidence found.
CVSS exploit maturity: proof of concept public
Exploited in the wildExploited: no evidence on record.
Not in CISA KEV and no source reports exploitation
Observed by OffSeq MirageSeen by Mirage: no evidence on record.
No attack traffic recorded by OffSeq Mirage sensors

A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), CVSS vector, the Metasploit, Exploit-DB and nuclei-templates index as of 26 Oct 2026.

Disclosed: The CVE record is public on cve.org. Its publication is t = 0.
Detectable: A public nuclei template can find exposed instances, for defenders and attackers alike.
Weaponised: Public exploit code exists in Metasploit or Exploit-DB, or CISA SSVC or the CVSS exploit maturity reports a public proof of concept.
Exploited in the wild: CISA KEV lists it, CISA SSVC rates exploitation active, or a source reports attacks.
Observed by OffSeq Mirage: OffSeq Mirage honeypot sensors recorded attack traffic for this CVE, or found exposed hosts without attack traffic.

Moments are spaced evenly, not to scale; a dashed line marks a gap of six months or more. Deltas count from t = 0. Sources that give only a date (CISA KEV, Exploit-DB, or a time of exactly 00:00Z) read “same day” rather than hours. Metasploit modules carry the flaw’s disclosure date, not their release date, and nuclei templates carry no date, so both appear above but not on the timeline.

What to do

Affected software

Product	Affected	Fixed in
PyPIletta-ai/letta`pkg:pypi/letta-ai/letta`Other threats	Affected =0.4.0 =0.4.1	Fixed in–

Check your own hosts for these packages with threat-finder (opens in a new tab), our free open-source scanner.

AI-suggested

Immediate mitigation should focus on restricting access to the letta-ai letta service to trusted network segments only, minimizing exposure to adjacent network attackers.
Implement strict input validation and sanitization on all inputs to the function_message function, especially function_name and function_args, to neutralize any potentially malicious directives before dynamic evaluation.
Employ runtime application self-protection (RASP) or similar monitoring tools to detect anomalous code execution patterns indicative of exploitation attempts.
If possible, disable or limit dynamic code evaluation features in letta until a patched version is available.
Monitor vendor communications closely for official patches or updates addressing this vulnerability and apply them promptly.
Conduct internal audits of AI-related workflows using letta to identify and isolate critical data or processes that could be targeted.
Enhance network segmentation and implement strict access controls to reduce the risk of lateral movement by attackers exploiting this vulnerability.
Educate development and operations teams about the risks of dynamic code evaluation and enforce secure coding practices to prevent similar issues in future releases.

Description

A vulnerability classified as critical has been found in letta-ai letta up to 0.4.1. Affected is the function function_message of the file letta/letta/interface.py. The manipulation of the argument function_name/function_args leads to improper neutralization of directives in dynamically evaluated code. The exploit has been disclosed to the public and may be used.

Impact

For European organizations utilizing letta-ai letta versions 0.4.0 or 0.4.1, this vulnerability could lead to unauthorized code execution within the context of the affected application. Although the CVSS score is medium (5.1), the risk is non-trivial because exploitation requires only low privileges and no user interaction, potentially allowing lateral movement or targeted attacks within internal networks. The impact on confidentiality could involve leakage of sensitive information processed by the application. Integrity could be compromised through unauthorized modification of data or execution flow, and availability could be affected if malicious code disrupts service operations. Organizations in sectors relying on AI-driven automation or data processing using letta may face operational disruptions or data integrity issues. Given the adjacency network attack vector, internal network security posture is critical; compromised internal hosts could be leveraged to exploit this vulnerability. The absence of known exploits in the wild currently reduces immediate risk but does not eliminate it, especially post-public disclosure. European entities with sensitive AI workloads or critical infrastructure automation using letta should consider this vulnerability a moderate threat requiring timely mitigation.

References

Community reviews

Loading reviews…

Exploitation evidence

What to do

Affected software

Description

AI analysisMachine-generated, updated 16 Jun 2025, 02:49 UTC

Technical details

References

Community reviews

Related threats