PT-2026-28690

A security vulnerability has been detected in letta-ai letta 0.16.4. This vulnerability affects the function convert message create to message of the file letta/helpers/message helper.py of the component File URL Handler. Such manipulation of the argument ImageContent leads to server-side request...

PT-2026-28691

Name of the Vulnerable Software and Affected Versions letta-ai letta version 0.16.4 Description A flaw exists in the resolve type function within the letta/functions/ast parsers.py file. This issue involves improper neutralization of directives in dynamically evaluated code, potentially allowing...

Letta-ai letta 安全漏洞

Letta-ai letta is an open-source stateful proxy framework developed by Letta-ai, featuring memory management, reasoning capabilities, and context handling. Version 0.16.4 of letta-ai letta contains a security vulnerability. This vulnerability arises from incorrect operations on functions in the...

Letta-ai letta 安全漏洞

Letta-ai letta is an open-source stateful proxy framework developed by Letta-ai, featuring memory management, reasoning capabilities, and context handling. Version 0.16.4 of Letta-ai letta contains a security vulnerability caused by incorrect handling of the parameter ImageContent in the file...

EUVD-2025-22345

Malicious code in bioql PyPI...

CVE-2025-51482

Remote Code Execution in letta.server.restapi.routers.v1.tools.runtoolfromsource in letta-ai Letta 0.7.12 allows remote attackers to execute arbitrary Python code and system commands via crafted payloads to the /v1/tools/run endpoint, bypassing intended sandbox restrictions...

Arbitrary Code Injection

Overview letta is a Create LLM agents with long-term memory and custom tools Affected versions of this package are vulnerable to Arbitrary Code Injection via the runlocaldirsandboxdirectly function in the toolexecutionsandbox.py file. An attacker can execute arbitrary Python code and system...

CVE-2025-51482

Remote Code Execution in letta.server.restapi.routers.v1.tools.runtoolfromsource in letta-ai Letta 0.7.12 allows remote attackers to execute arbitrary Python code and system commands via crafted payloads to the /v1/tools/run endpoint, bypassing intended sandbox restrictions...

PT-2025-30443 · Letta-Ai · Letta

Name of the Vulnerable Software and Affected Versions: letta versions 0.7.12 Description: A remote code execution issue exists in letta.server.rest api.routers.v1.tools.run tool from source within letta-ai Letta. The vulnerability allows remote attackers to execute arbitrary Python code and syste...

CVE-2025-51482

Remote Code Execution in letta.server.restapi.routers.v1.tools.runtoolfromsource in letta-ai Letta 0.7.12 allows remote attackers to execute arbitrary Python code and system commands via crafted payloads to the /v1/tools/run endpoint, bypassing intended sandbox restrictions...

Letta-ai letta 代码注入漏洞

Letta-ai letta is a stateful agent framework with memory, inference, and context management from the Letta-ai open source. A security vulnerability exists in Letta-ai letta version 0.7.12, which originates in the /v1/tools/run endpoint and allows the execution of arbitrary Python code and system...

CVE-2025-51482

Remote Code Execution in letta.server.restapi.routers.v1.tools.runtoolfromsource in letta-ai Letta 0.7.12 allows remote attackers to execute arbitrary Python code and system commands via crafted payloads to the /v1/tools/run endpoint, bypassing intended sandbox restrictions...

CVE-2025-51482

Letta Letta 0.7.12 is vulnerable to remote code execution via POST /v1/tools/run (run_tool_from_source) in letta.server.rest_api.routers.v1.tools.run_tool_from_source. The underlying issue allows an unauthenticated attacker to execute arbitrary Python code and OS commands by sending crafted tool ...

CVE-2025-51482

Remote Code Execution in letta.server.restapi.routers.v1.tools.runtoolfromsource in letta-ai Letta 0.7.12 allows remote attackers to execute arbitrary Python code and system commands via crafted payloads to the /v1/tools/run endpoint, bypassing intended sandbox restrictions...

CVE-2025-6101

A vulnerability classified as critical has been found in letta-ai letta up to 0.4.1. Affected is the function functionmessage of the file letta/letta/interface.py. The manipulation of the argument functionname/functionargs leads to improper neutralization of directives in dynamically evaluated...

CVE-2025-6101

A vulnerability classified as critical has been found in letta-ai letta up to 0.4.1. Affected is the function functionmessage of the file letta/letta/interface.py. The manipulation of the argument functionname/functionargs leads to improper neutralization of directives in dynamically evaluated...

Eval Injection

Overview letta is a Create LLM agents with long-term memory and custom tools Affected versions of this package are vulnerable to Eval Injection via the functionmessage process. An attacker can execute arbitrary code by manipulating the functionname or functionargs arguments. Remediation There is ...

letta-nory (0.1.0) potentially affected by CVE-2025-6101 via letta (0.16.8)

letta PYPI version 0.16.8 is affected by a known vulnerability. The following packages have a transitive dependency on letta and may be impacted: - letta-nory 0.1.0 Source cves: CVE-2025-6101 Source advisory: SNYK:PYTHON-LETTA-10494065...

CVE-2025-6101 letta-ai letta interface.py function_message eval injection

A vulnerability classified as critical has been found in letta-ai letta up to 0.4.1. Affected is the function functionmessage of the file letta/letta/interface.py. The manipulation of the argument functionname/functionargs leads to improper neutralization of directives in dynamically evaluated...

CVE-2025-6101 letta-ai letta interface.py function_message eval injection

A vulnerability classified as critical has been found in letta-ai letta up to 0.4.1. Affected is the function functionmessage of the file letta/letta/interface.py. The manipulation of the argument functionname/functionargs leads to improper neutralization of directives in dynamically evaluated...