CVE-2026-45387

Open WebUI vulnerability CVE-2026-45387 affects Open WebUI (self-hosted offline AI) prior to version 0.9.5, where granting a group read access to a model could let other users view the model’s system prompt. Root cause: read-permission exposure of confidential prompt data. Impact: potential leaka...

CVE-2026-45387 Open WebUI: Sharing models for others to use (read permission) also exposes model details (system prompt leakage)

Open WebUI is a self-hosted artificial intelligence platform designed to operate entirely offline. Prior to 0.9.5, when setting model permissions so that a group has read access to it, intending for other users to use it, those users also can read the model's system prompt. However users may...

CVE-2026-45539

Microsoft APM is an open-source, community-driven dependency manager for AI agents. From 0.5.4 to 0.12.4, two primitive integrators in apm-cli enumerate package files with bare Path.glob / Path.rglob calls and read each match with Path.readtext, transparently following symbolic links. A symlink...

CVE-2026-45539 Microsoft APM: Symlinks under `.apm/prompts/` and `.apm/agents/` are dereferenced during `apm install`, copying host-local file contents into the project tree

Microsoft APM is an open-source, community-driven dependency manager for AI agents. From 0.5.4 to 0.12.4, two primitive integrators in apm-cli enumerate package files with bare Path.glob / Path.rglob calls and read each match with Path.readtext, transparently following symbolic links. A symlink...

CVE-2026-45539

Microsoft APM (APM CLI) vulnerability affects versions 0.5.4–0.12.4 where two primitive integrators enumerate package files via Path.glob/Path.rglob and read matches with Path.read_text(), following symbolic links. A symlink inside a remote APM dependency under .apm/prompts/ or .apm/agents/ is pr...

CVE-2026-45539 Microsoft APM: Symlinks under `.apm/prompts/` and `.apm/agents/` are dereferenced during `apm install`, copying host-local file contents into the project tree

Microsoft APM is an open-source, community-driven dependency manager for AI agents. From 0.5.4 to 0.12.4, two primitive integrators in apm-cli enumerate package files with bare Path.glob / Path.rglob calls and read each match with Path.readtext, transparently following symbolic links. A symlink...

Open WebUI 信息泄露漏洞

Open WebUI is an extensible, feature-rich, and user-friendly self-hosted WebUI under open source. Versions of Open WebUI prior to 0.8.9 contained a vulnerability related to information leakage. This vulnerability occurred when non-administrator users logged in, causing the application to send...

Insertion of Sensitive Information Into Sent Data

Overview open-webui is an Open WebUI Affected versions of this package are vulnerable to Insertion of Sensitive Information Into Sent Data through the getmodelbyid handler in routers/models.py. An attacker can read the admin-curated system prompt and other model behavior settings by sending a GET...

Open WebUI Exposes System Prompt to Regular User [Non-Admin]

Summary A regular user non-admin can view the system prompt of the model which is set by an admin. Details When a regular user non-admin logs into the application, a http://IP:8080/api/models? web request is initiated by the application and in response, it reveals the system prompt of available...

Information Exposure

Overview open-webui is an Open WebUI Affected versions of this package are vulnerable to Information Exposure via the api/models endpoint. An attacker can access sensitive system prompt information by sending authenticated requests as a non-admin user. Remediation Upgrade open-webui to version...

GHSA-JH9G-8JQW-M2QX Open WebUI Exposes System Prompt to Regular User [Non-Admin]

Summary A regular user non-admin can view the system prompt of the model which is set by an admin. Details When a regular user non-admin logs into the application, a http://IP:8080/api/models? web request is initiated by the application and in response, it reveals the system prompt of available...

CVE-2025-69443

Remote Code Execution in coleam00 Archon 0.1.0. A crafted HTML page, when accessed by a victim, can execute commands, run prompts on behalf of the user, control the Archon UI features, and steal all Archon information available on the UI including API keys...

Deserialization of Untrusted Data

Overview langchain is a Building applications with LLMs through composability Affected versions of this package are vulnerable to Deserialization of Untrusted Data when fetching and processing prompt manifests from external sources. An attacker can execute arbitrary code or manipulate application...

GHSA-3644-Q5CJ-C5C7 LangSmith SDK: Public prompt pull deserializes untrusted manifests without trust boundary warning

Description The LangSmith SDK's prompt pull methods pullprompt / pullpromptcommit in Python, pullPrompt / pullPromptCommit in JS/TS fetch and deserialize prompt manifests from the LangSmith Hub. These manifests may contain serialized LangChain objects and model configuration that affect runtime...

CVE-2026-42203

A flaw was found in LiteLLM, an AI Gateway. An authenticated user could exploit this by sending a crafted prompt template to the POST /prompts/test endpoint. The endpoint rendered user-supplied prompt templates without proper sandboxing. This could lead to arbitrary code execution within the...

agentcore-poc

Blueprint POC - Workflow Generation & Deployment A Proof of C...

MAL-2026-3683 Malicious code in @dropout-ai/runtime (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 2121b923a39177ed68ce5cf066cbb07891b7cb5d20ecf5ec66f2c953634eff10 On require/import, src/index.js replaces global.fetch with a wrapper that intercepts every fetch whose URL matches openai.com, anthropic.com,...

Malicious code in @dropout-ai/runtime (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 2121b923a39177ed68ce5cf066cbb07891b7cb5d20ecf5ec66f2c953634eff10 On require/import, src/index.js replaces global.fetch with a wrapper that intercepts every fetch whose URL matches openai.com, anthropic.com,...

PT-2026-40723

Name of the Vulnerable Software and Affected Versions LangSmith SDK Python versions prior to 0.8.0 LangSmith SDK JS/TS versions prior to 0.6.0 Description The prompt pull methods pull prompt and pull prompt commit in Python, and pullPrompt and pullPromptCommit in JS/TS, fetch and deserialize prom...

CVE-2026-44246 nnU-Net: Agentic workflow injection in `.github/workflows/issue-triage.yml` of `MIC-DKFZ/nnUNet`

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 allowednonwriteusers: $...