CVE-2025-9959

Incomplete validation of dunder attributes allows an attacker to escape from the Local Python execution environment sandbox, enforced by smolagents. The attack requires a Prompt Injection in order to trick the agent to create malicious code...

CVE-2025-9959 Sandbox escape in smolagents Local Python execution environment via dunder attributes

Incomplete validation of dunder attributes allows an attacker to escape from the Local Python execution environment sandbox, enforced by smolagents. The attack requires a Prompt Injection in order to trick the agent to create malicious code...

CVE-2025-9959 Sandbox escape in smolagents Local Python execution environment via dunder attributes

Incomplete validation of dunder attributes allows an attacker to escape from the Local Python execution environment sandbox, enforced by smolagents. The attack requires a Prompt Injection in order to trick the agent to create malicious code...

CVE-2025-9959 Sandbox escape in smolagents Local Python execution environment via dunder attributes

Incomplete validation of dunder attributes allows an attacker to escape from the Local Python execution environment sandbox, enforced by smolagents. The attack requires a Prompt Injection in order to trick the agent to create malicious code...

CVE-2025-9959

CVE-2025-9959 concerns smolagents, a Python agents library. The root issue is incomplete validation of dunder attributes, enabling an attacker to escape the Local Python execution environment sandbox when a Prompt Injection is used to coax the agent into creating malicious code. Several connected...

CVE-2025-9959

Incomplete validation of dunder attributes allows an attacker to escape from the Local Python execution environment sandbox, enforced by smolagents. The attack requires a Prompt Injection in order to trick the agent to create malicious code...

Indirect Prompt Injection Attacks Against LLM Assistants

Really good research on practical attacks against LLM agents. "Invitation Is All You Need! Promptware Attacks Against LLM-Powered Assistants in Production Are Practical and Dangerous" Abstract: The growing integration of LLMs into applications has introduced new security risks, notably known as...

CVE-2025-9959: Improper Control of Generation of Code

Incomplete validation of dunder attributes allows an attacker to escape from the Local Python execution environment sandbox, enforced by smolagents. The attack requires a Prompt Injection in order to trick the agent to create malicious code...

PT-2025-35805

Name of the Vulnerable Software and Affected Versions smolagents affected versions not specified Description Incomplete validation of dunder attributes allows an attacker to escape from the Local Python execution environment sandbox enforced by the software. The attack requires a Prompt Injection...

CVE-2025-22422

In multiple locations, there is a possible way to mislead a user into approving an authentication prompt for one app when its result will be used in another due to a logic error in the code. This could lead to local escalation of privilege with no additional execution privileges needed. User...

CVE-2025-22422

In multiple locations, there is a possible way to mislead a user into approving an authentication prompt for one app when its result will be used in another due to a logic error in the code. This could lead to local escalation of privilege with no additional execution privileges needed. User...

CVE-2025-22422

In multiple locations, there is a possible way to mislead a user into approving an authentication prompt for one app when its result will be used in another due to a logic error in the code. This could lead to local escalation of privilege with no additional execution privileges needed. User...

CVE-2025-22422

A logic error in the Framework component of Google Android allows an attacker to mislead users into approving an authentication prompt for one app when the result is utilized by another. This vulnerability enables local escalation of privilege without requiring additional execution privileges or ...

CVE-2025-22422

In multiple locations, there is a possible way to mislead a user into approving an authentication prompt for one app when its result will be used in another due to a logic error in the code. This could lead to local escalation of privilege with no additional execution privileges needed. User...

CVE-2025-22422

In multiple locations, there is a possible way to mislead a user into approving an authentication prompt for one app when its result will be used in another due to a logic error in the code. This could lead to local escalation of privilege with no additional execution privileges needed. User...

PT-2025-35626

Name of the Vulnerable Software and Affected Versions: affected versions not specified Description: A logic error in the code may mislead a user into approving an authentication prompt for one application when the result is used in another. This could lead to local escalation of privilege without...

Linux Distros Unpatched Vulnerability : CVE-2024-39894

The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - OpenSSH 9.5 through 9.7 before 9.8 sometimes allows timing attacks against echo-off password entry e.g., for su and Sudo because of an ObscureKeystrokeTiming...

CVE-2025-9799

A security flaw has been discovered in Langfuse up to 3.88.0. Affected by this vulnerability is the function promptChangeEventSourcing of the file web/src/features/prompts/server/routers/promptRouter.ts of the component Webhook Handler. Performing manipulation results in server-side request...

CVE-2025-9799 Langfuse Webhook promptRouter.ts promptChangeEventSourcing server-side request forgery

A security flaw has been discovered in Langfuse up to 3.88.0. Affected by this vulnerability is the function promptChangeEventSourcing of the file web/src/features/prompts/server/routers/promptRouter.ts of the component Webhook Handler. Performing manipulation results in server-side request...

langfuse 代码问题漏洞

langfuse is a large language model engineering platform open-sourced by Langfuse. A code issue vulnerability exists in langfuse 3.88.0 and earlier versions, which stems from a misuse of the function promptChangeEventSourcing in the file web/src/features/prompts/server/routers/promptRouter.ts...