EUVD-2026-71143

LaVague 0.2.35 contains a remote code execution vulnerability in PythonFromMarkdownExtractor.extractasobject that evaluates untrusted language model output derived from web page content. Attackers can inject malicious Python code through web pages using indirect prompt injection to execute...

CVE-2026-85689 llmware 0.4.6 SQL Injection via unescaped filter values

llmware 0.4.6 contains an SQL injection vulnerability in the collection-database layer llmware/resources.py where filter and lookup values are directly string-interpolated into SQL WHERE clauses without parameterization or escaping, in both the SQLite and PostgreSQL backends. The filter validator...

CVE-2026-85689

llmware 0.4.6 contains an SQL injection vulnerability in its collection-database layer (llmware/resources.py). Filter and lookup values are directly string-interpolated into SQL WHERE clauses without parameterization or escaping, affecting both the SQLite and PostgreSQL backends. The filter valid...

EUVD-2026-71138

llmware 0.4.6 contains an SQL injection vulnerability in the collection-database layer llmware/resources.py where filter and lookup values are directly string-interpolated into SQL WHERE clauses without parameterization or escaping, in both the SQLite and PostgreSQL backends. The filter validator...

CVE-2026-85689 llmware 0.4.6 SQL Injection via unescaped filter values

llmware 0.4.6 contains an SQL injection vulnerability in the collection-database layer llmware/resources.py where filter and lookup values are directly string-interpolated into SQL WHERE clauses without parameterization or escaping, in both the SQLite and PostgreSQL backends. The filter validator...

CVE-2026-85675 OWL DocumentProcessingToolkit Server-Side Request Forgery via URL Fetching

OWL's DocumentProcessingToolkit contains a server-side request forgery vulnerability in the extractdocumentcontent tool that fetches caller-supplied URLs with no scheme, host, or IP filtering. Attackers can inject malicious URLs through prompt injection to make the server fetch internal resources...

CVE-2026-85675

OWL 's DocumentProcessingToolkit contains a server-side request forgery (SSRF) vulnerability in the extract_document_content tool. The tool fetches caller-supplied URLs without scheme, host, or IP filtering , allowing attackers to inject malicious URLs via prompt injection and cause the server to...

EUVD-2026-71130

aider aider-chat automatically loads a .aider.conf.yml configuration file from the root of the git repository it is launched in. A crafted repository can set test-cmd executed at startup or lint-cmd executed on the first file edit, which aider runs through a shell subprocess with shell=True witho...

EUVD-2026-71131

OWL's DocumentProcessingToolkit contains a server-side request forgery vulnerability in the extractdocumentcontent tool that fetches caller-supplied URLs with no scheme, host, or IP filtering. Attackers can inject malicious URLs through prompt injection to make the server fetch internal resources...

CVE-2026-85672 zerox 1.1.20 OS Command Injection via Document URL File Extension

zerox 1.1.20 contains an OS command injection vulnerability in the file download mechanism where the temporary file extension derived from document URLs is interpolated unsanitized into shell commands executed by poppler utilities. Attackers can craft document URLs with malicious file extensions...

EUVD-2026-71128

zerox 1.1.20 contains an OS command injection vulnerability in the file download mechanism where the temporary file extension derived from document URLs is interpolated unsanitized into shell commands executed by poppler utilities. Attackers can craft document URLs with malicious file extensions...

CVE-2026-85672

zerox 1.1.20 (getomni-ai) is affected by an OS command injection in its file download mechanism. The temporary file extension derived from document URLs is interpolated unsanitized into shell commands executed by poppler utilities. An attacker can craft a document URL with a malicious file extens...

CVE-2026-85667 xiaobei through 5.5.2 Unauthenticated Webhook Message Injection

xiaobei through 5.5.2 fails to implement authentication or signature validation on webhook endpoints, allowing unauthenticated attackers to inject arbitrary messages into the agent pipeline. Attackers can publish malicious messages via the /webhookworktool handler and exploit unvalidated media UR...

CVE-2026-85667

xiaobei through 5.5.2 fails to implement authentication or signature validation on its webhook endpoints, specifically the /webhook_worktool handler. This allows unauthenticated network attackers to inject arbitrary messages into the agent pipeline and exploit unvalidated media URL fetching to pe...

EUVD-2026-71123

xiaobei through 5.5.2 fails to implement authentication or signature validation on webhook endpoints, allowing unauthenticated attackers to inject arbitrary messages into the agent pipeline. Attackers can publish malicious messages via the /webhookworktool handler and exploit unvalidated media UR...

CVE-2026-85667 xiaobei through 5.5.2 Unauthenticated Webhook Message Injection

xiaobei through 5.5.2 fails to implement authentication or signature validation on webhook endpoints, allowing unauthenticated attackers to inject arbitrary messages into the agent pipeline. Attackers can publish malicious messages via the /webhookworktool handler and exploit unvalidated media UR...

CVE-2026-85663 Aim 3.29.1 Remote Code Execution via Unauthenticated Method Dispatch

Aim 3.29.1 remote tracking server fails to authenticate requests and dispatches arbitrary methods through getattr without allowlist validation. Unauthenticated attackers can register clients, instantiate Repo resources, and invoke arbitrary methods to read experiments or delete runs...

EUVD-2026-71116

cli-mcp-server 0.2.5 contains a command allowlist bypass vulnerability in the validatecommandwithoperators function when ALLOWSHELLOPERATORS is enabled. Attackers can use shell command substitution syntax like $... or backticks to execute non-allowlisted commands that bypass the ALLOWEDCOMMANDS...

CVE-2026-85660

cli-mcp-server 0.2.5 contains a command allowlist bypass in the _validate_command_with_operators function. When ALLOW_SHELL_OPERATORS is enabled, an attacker can inject shell command substitution syntax such as $(...) or backticks to execute commands that are not on the ALLOWED_COMMANDS allowlist...

EUVD-2026-71233

git-mcp-server 2.15.1 contains an argument injection vulnerability in the ref and object parameters of gitlog, gitdiff, and gitshow tools that lack leading-dash validation. Attackers can inject git command-line options like --output= to write files outside the repository to arbitrary paths...