| CVE |
Vendors |
Products |
Updated |
CVSS v3.1 |
| A transient execution vulnerability in some AMD processors may allow an attacker with the ability to execute code on the system to infer data in the L1D cache, potentially resulting in the leakage of sensitive information across privileged boundaries. |
| A transient execution vulnerability in some AMD processors may allow an attacker to infer data in the L1D cache, potentially resulting in the leakage of sensitive information across privileged boundaries. |
| A transient execution vulnerability in some AMD processors may allow an attacker to infer data from previous stores, potentially resulting in the leakage of privileged information. |
| OpsTree REMS through 1.0.0 contains a prompt injection vulnerability that allows authenticated users to disclose the hidden system prompt by submitting crafted chat input to POST /api/v1/rca/chat. Attackers can instruct the assistant to ignore its rules and reveal internal orchestration instructions, aiding the crafting of further prompt injection attacks. |
| EDK2 contains a vulnerability in BIOS
where a privileged attacker may cause “Exposure of Sensitive Information during
Transient Execution” by local access. Successful exploitation of
this vulnerability may result in disclosure of SMRAM contents. It could also impact Confidentiality. |
| A security vulnerability has been detected in esengine DeepSeek-Reasonix up to 2.52.0. Affected is the function discoverDocs of the file internal/memory/doc.go. The manipulation leads to improper neutralization of input used for llm prompting. The attack can be initiated remotely. The exploit has been disclosed publicly and may be used. Upgrading to version 2.53.0 is able to address this issue. The identifier of the patch is 4ca33493a673c2788aa8598fbca2b2f47a69e1b8. It is suggested to upgrade the affected component. |
| Improper neutralization of input used for LLM prompting vulnerability in Johnson Controls EasyIO Neo IO Manager and Tools Installer allows Search Order Hijacking.
This issue affects EasyIO Neo IO Manager and Tools Installer: 1.1.0.0. |
| OpenHuman is an open-source agent harness available as a desktop application and Rust library. Before 0.57.13, OpenHuman places names, descriptions, titles, and parameter definitions returned by configured external MCP servers into the agent model context without neutralizing instructions or bounding the descriptive fields. The McpRemoteTool records produced by list_tools preserve this remote content, while tool filtering considers the tool name and the prompt-injection detector screens user messages rather than MCP definitions. A malicious or compromised MCP server can therefore return a poisoned description that is evaluated on every agent turn and may direct the model to invoke other available tools, disclose accessible data, or perform unauthorized actions without a separate malicious user message. The issue affects users who configure an attacker-controlled or compromised MCP server. This issue is fixed in version 0.57.13. |
| Vikunja veans before 2.7.1 contains a prompt injection vulnerability that allows project members with write access to inject instructions by setting project titles or task content rendered verbatim inside the coding agent's authoritative instruction block. Attackers can craft ProjectTitle or task descriptions that the prime hook loads on SessionStart and PreCompact, causing the agent to modify the developer's checkout or run commands. |
| Lavish is the new editor for your HTML artifacts. Prior to 0.1.43, the lavish-axi loopback HTTP server did not authenticate requests or validate Host and Origin values on session, artifact, prompt, and polling routes. A website visited while the server is running can use DNS rebinding to send same-origin browser requests to the local service. POST /api/sessions accepts a caller-selected file path and returns its deterministic session key; GET /artifact/:key/index.html then returns the file contents, allowing disclosure of any file readable by the server process without an existing session. An attacker can also queue text through POST /api/:key/prompts for an active agent session when the artifact path is known or guessed. Visiting the attacker-controlled website is the required user interaction. This vulnerability is fixed in 0.1.43. |
| Sogou Input Method for Windows contains a vulnerability in the configuration retrieval mechanism of its SGTool.exe component. The application retrieves configuration data over unencrypted HTTP connections, allowing an attacker capable of manipulating network traffic to replace legitimate server responses with malicious configurations. An attacker can exploit this vulnerability to instruct SGTool.exe to download attacker-controlled files to arbitrary locations, including paths used by legitimate application components. This can result in arbitrary code execution when the downloaded files are subsequently executed or loaded by the application. |
| OpenHuman is an open-source agent harness available as a desktop application and Rust library. Before 0.57.13, background synchronization for connected services such as email, Slack, and Notion stores raw external content and later places it in the model context of autonomous background agents without neutralizing embedded instructions. ApprovalGate treats tool calls without an interactive chat context as pre-authorized automation, so attacker-authored content processed during a background tick can influence the model to invoke Composio actions without presenting an approval request. An attacker who can deliver content to a connected account can use this path to send or forward data, post messages, create or modify third-party content, or disclose information from OpenHuman memory and integrations. The issue requires an active integration and successful model interpretation of the injected instructions. This issue is fixed in version 0.57.13. |
| Improper neutralization of input used for LLM prompting in the environment tool in Strands Agents Tools before 0.8.6 might allow remote actors to obtain the agent host's environment variables in cleartext, including cloud credentials and API keys, via a crafted prompt that disables the tool's secret masking.
To remediate this issue, users should upgrade to version 0.8.6 or later and rotate any credentials that were present in the environment of agents that loaded the environment tool. |
| Context7 through 2.1.2 contains a prompt injection vulnerability that allows attackers to execute malicious instructions in connected AI coding agents by injecting unsanitized content through the Custom AI Instructions feature served via the MCP server. Attackers can poison the custom instructions to exfiltrate credentials from environment files to an attacker-controlled service and perform destructive file deletion on the victim's machine when the agent makes a routine library documentation request. |
| Exposure of Sensitive Information in Shared Microarchitectural Structures during Transient Execution for some Intel(R) Processors may allow an authenticated user to potentially enable information disclosure via local access. |
| Exposure of sensitive information caused by shared microarchitectural predictor state that influences transient execution for some Intel(R) Processors within VMX non-root (guest) operation may allow an information disclosure. Unprivileged software adversary with an authenticated user combined with a high complexity attack may enable data exposure. This result may potentially occur via local access when attack requirements are present without special internal knowledge and requires no user interaction. The potential vulnerability may impact the confidentiality (high), integrity (none) and availability (none) of the vulnerable system, resulting in subsequent system confidentiality (high), integrity (none) and availability (none) impacts. |
| Improper neutralization of input used for llm prompting in Microsoft Edge for iOS allows an unauthorized attacker to perform spoofing over a network. |
| Improper neutralization of input used for LLM prompting in the python_repl tool in Amazon Strands Agents Tools before 0.8.5 might allow remote actors to execute arbitrary Python code on the agent's host by bypassing the human consent gate, via a crafted prompt that forwards non_interactive_mode as a keyword argument through the batch tool. To remediate this issue, users should upgrade to version 0.8.5 or later. |
| The Windows interactive service in OpenVPN 2.7_alpha1 through 2.7.4 allows remote attackers to cause persistent DNS state pollution or a service crash via a crafted search domain during the disconnection process |
| A prompt injection vulnerability in the shell tool in Amazon Strands Agents Tools before 0.8.0 might allow remote actors to execute arbitrary operating system commands on the agent's host via a crafted prompt that sets the non_interactive parameter to true, bypassing the human consent gate.
To remediate this issue, users should upgrade to version 0.8.0. |
