| CVE |
Vendors |
Products |
Updated |
CVSS v3.1 |
| 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. |
| 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. |
| 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. |
| 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. |
| 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. |
| 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. |
| MoviePilot through 3.1.5 contains a command injection vulnerability that allows attackers to execute arbitrary OS commands by embedding malicious instructions in untrusted content processed through tools like browse_webpage, search_web, and torrent metadata parsers, which then get passed to the unrestricted ExecuteCommandTool via asyncio.create_subprocess_shell. Attackers can craft content that instructs the model to invoke execute_command with confirm_dangerous set to true, bypassing the validate_command_safety denylist and exploiting the admin session's is_admin context to achieve remote code execution on the host. |
| LangAlpha through 2026.09.07 contains an indirect prompt injection vulnerability that allows remote attackers to execute shell commands or Python by planting instructions in web content retrieved by the agent. Because Bash and ExecuteCode lack an allow-list and human-in-the-loop approval, attackers can run code in the workspace sandbox and exfiltrate vault secrets from _internal/.vault_secrets.json. |
| HKUDS Vibe-Trading from 0.1.0 before 0.1.7 contains an indirect prompt injection vulnerability that allows remote attackers to execute shell commands as root by planting instructions in documents or web pages the agent processes. BashTool and BackgroundRunTool pass model-emitted commands to subprocess.run with shell=True and no allow-list or approval step, and read_url fetches arbitrary URLs, enabling command execution and server-side request forgery. |
| GitLab has remediated an issue in GitLab EE affecting all versions from 19.1 before 19.2.8, 19.3 before 19.3.5, and 19.4 before 19.4.2 that, under certain conditions, could have allowed an authenticated user to inject specially crafted content into AI agent instructions, potentially causing unintended command execution attributed to other users, due to improper neutralization of special elements in AI conversation context construction. |
| 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. |
| 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. |
| HCL AION is affected by a vulnerability where indirect prompt injection can lead to HTML injection in rendered output. Injected markup may be displayed to users, potentially resulting in unintended behavior or security impact under certain conditions. |
| 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. |
| GitLab has remediated an issue in GitLab EE affecting all versions from 19.1 before 19.1.3 and 19.2 before 19.2.1 that under certain conditions could have allowed an authenticated user to access information from unauthorized projects due to improper neutralization of untrusted content processed by the AI-assisted code review functionality. |
| In Eclipse Theia versions prior to 1.71.0, the AI chat agent processed workspace file and directory names as part of its prompt context without distinguishing them from system instructions. An attacker could craft a malicious repository with adversarial directory or file names that, when analyzed by the AI agent, would cause the agent to follow attacker-controlled instructions (indirect prompt injection). Combined with other AI chat features available in untrusted workspaces, this enabled attack chains leading to data exfiltration via Markdown image rendering or arbitrary command execution via task definitions. |
| In Eclipse Theia versions prior to 1.71.0, files matching the pattern .prompts/*.prompttemplate in a workspace were automatically loaded and could override or extend the AI agent's system prompts. An attacker could craft a malicious repository containing prompt template files that, when the workspace was opened in Theia, replaced the AI's system instructions with attacker-controlled content (indirect prompt injection). Combined with other AI chat features available in untrusted workspaces, this enabled attack chains leading to data exfiltration via Markdown image rendering or arbitrary command execution via task definitions. |
| nnU-Net is a semantic segmentation framework that automatically adapts its pipeline to a dataset. Prior to 2.4.1, the nnU-Net Issue Triage workflow in .github/workflows/issue-triage.yml is vulnerable to Agentic Workflow Injection. The workflow sets allowed_non_write_users: ${{ github.event.issue.user.login }}, which means any logged-in GitHub user who opens an issue can reach this agentic workflow with attacker-controlled content. Untrusted issue title and body content are embedded directly into the prompt of anthropics/claude-code-action, and the workflow then runs a command-capable Claude agent with permission to comment on and relabel the current issue via gh. Because this workflow is triggered automatically on issues.opened, an external attacker can submit a crafted issue that steers the agent beyond its intended issue-triage purpose and influences authenticated issue actions. This vulnerability is fixed in 2.4.1. |
| MCP Calculate Server is a mathematical calculation service based on MCP protocol and SymPy library. Prior to 0.1.1, the use of eval() to evaluate mathematical expressions without proper input sanitization leads to remote code execution. This vulnerability is fixed in 0.1.1. |
