VulnWatch VulnWatch

AI Security Dashboard

Curated vulnerabilities, advisories, and breaches affecting AI/ML systems.

Total Entries
2,510
Critical
324
Actively Exploited
9
Last 24h
6

Get the weekly digest

Top AI security stories every Monday. Free, no spam. Want it daily? See Daily Briefing.

Critical nvd

CVE-2026-61808: LightRAG provides simple and fast retrieval-augmented generation. Through version 1.5.4, the LightRAG API server binds t

LightRAG provides simple and fast retrieval-augmented generation. Through version 1.5.4, the LightRAG API server binds to all network interfaces with authentication disabled by default, allowing an un...

llm
9.8
CVSS
10 hours ago
Critical nvd

CVE-2026-48039: Meta Ads MCP is a Model Context Protocol (MCP) server that lets AI assistants run Meta Ads. Prior to version 1.0.109, `A

Meta Ads MCP is a Model Context Protocol (MCP) server that lets AI assistants run Meta Ads. Prior to version 1.0.109, `AuthInjectionMiddleware.dispatch()` at `http_auth_integration.py:272` uncondition...

Agentic / MCP model context protocol
9.1
CVSS
10 hours ago
Critical nvd

CVE-2026-43632: llama.cpp builds b7492 through the latest b9060 contains a use-after-free vulnerability in llama-server affecting six to

llama.cpp builds b7492 through the latest b9060 contains a use-after-free vulnerability in llama-server affecting six tokenization endpoints (/tokenize, /detokenize, /infill, /apply-template, /rerank,...

anthropic llama
9.2
CVSS
1 day ago
Critical nvd

CVE-2026-43631: llama.cpp builds b7492 through the latest b9060 contains a use-after-free vulnerability in the vocab pointer of llama-se

llama.cpp builds b7492 through the latest b9060 contains a use-after-free vulnerability in the vocab pointer of llama-server when the --sleep-idle-seconds feature is enabled, allowing unauthenticated...

9.2
CVSS
1 day ago
Critical nvd

CVE-2026-43629: llama.cpp builds b4882 through b9058 contain a heap buffer overflow vulnerability in the KV cache state restore path whe

llama.cpp builds b4882 through b9058 contain a heap buffer overflow vulnerability in the KV cache state restore path where the state_read_data() function computes write size without overflow checking,...

9.2
CVSS
1 day ago
Critical nvd

CVE-2026-67531: FrontMCP is a TypeScript-first framework for the Model Context Protocol (MCP). Prior to 1.5.7, the sandboxed codecall:ex

FrontMCP is a TypeScript-first framework for the Model Context Protocol (MCP). Prior to 1.5.7, the sandboxed codecall:execute tool exposes live host Zod schema instances to the script via getTool(), a...

Prompt Injection Remote Code Execution Agentic / MCP model context protocol prompt injection indirect prompt
9.3
CVSS
2 days ago
Critical nvd

CVE-2026-48168: PraisonAI is a multi-agent teams system. In versions prior to 4.6.40, the bundled Claude GitHub Actions workflow is vuln

PraisonAI is a multi-agent teams system. In versions prior to 4.6.40, the bundled Claude GitHub Actions workflow is vulnerable to command injection because it embeds an attacker-controlled pull reques...

10.0
CVSS
2 days ago
Critical nvd

CVE-2026-70478: Flowise is a drag & drop user interface to build a customized large language model flow. Prior to 3.1.3, the POST /api/v

Flowise is a drag & drop user interface to build a customized large language model flow. Prior to 3.1.3, the POST /api/v1/oauth2-credential/refresh/:credentialId endpoint is included in WHITELIST_URLS...

large language model
9.2
CVSS
3 days ago
Critical nvd

CVE-2026-70477: Flowise is a drag & drop user interface to build a customized large language model flow. Prior to 3.1.3, a prompt inject

Flowise is a drag & drop user interface to build a customized large language model flow. Prior to 3.1.3, a prompt injection sent to a chatflow using a CSV Agent node can cause the LLM to respond with...

Prompt Injection large language model prompt injection llm
9.5
CVSS
3 days ago
Critical github

Flowise: CSV Agent Prompt Injection Remote Code Execution Vulnerability

-- ABSTRACT ------------------------------------- Trend Micro's Zero Day Initiative has identified a vulnerability affecting the following products: Flowise - Flowise -- VULNERABILITY DETAILS ------...

0.0
CVSS
3 days ago
Critical nvd

CVE-2026-70470: Flowise is a drag & drop user interface to build a customized large language model flow. Prior to 3.1.3, Flowise validat

Flowise is a drag & drop user interface to build a customized large language model flow. Prior to 3.1.3, Flowise validatePythonCodeForDataFrame in packages/components/src/pythonCodeValidator.ts can be...

large language model
9.5
CVSS
3 days ago
Critical github

Flowise: RCE via CSVAgent csvFile data URI base64 segment is interpolated into Python source without validation

### Summary Flowise's `CSVAgent` interpolates an attacker-controlled segment of the `csvFile` data URI directly into a Python source-code template that is then executed by Pyodide. Because Pyodide is...

0.0
CVSS
3 days ago
Critical github

Flowise: Pyodide validator Unicode homoglyph bypass leads to RCE

### Summary The validatePythonCodeForDataFrame blacklist in packages/components/src/pythonCodeValidator.ts can be bypassed with Unicode homoglyph identifiers, allowing arbitrary Python execution insid...

0.0
CVSS
3 days ago
Critical nvd

CVE-2026-69259: Flowise is a drag & drop user interface to build a customized large language model flow. Prior to 3.1.3, the SQLite Reco

Flowise is a drag & drop user interface to build a customized large language model flow. Prior to 3.1.3, the SQLite Record Manager node in packages/components/nodes/recordmanager/SQLiteRecordManager/S...

large language model
9.4
CVSS
3 days ago
Critical nvd

CVE-2026-69256: Flowise is a drag & drop user interface to build a customized large language model flow. Prior to 3.1.3, the CSVAgent no

Flowise is a drag & drop user interface to build a customized large language model flow. Prior to 3.1.3, the CSVAgent node allowed users to provide Python code that is executed through pyodide; althou...

Remote Code Execution large language model
9.4
CVSS
3 days ago
Critical nvd

CVE-2026-69255: Flowise is a drag & drop user interface to build a customized large language model flow. Prior to 3.1.3, the CSVAgent in

Flowise is a drag & drop user interface to build a customized large language model flow. Prior to 3.1.3, the CSVAgent in packages/components/nodes/agents/CSVAgent/CSVAgent.ts extracted attacker-contro...

large language model llm
9.2
CVSS
3 days ago
Critical nvd

CVE-2026-69254: Flowise is a drag & drop user interface to build a customized large language model flow. Prior to 3.1.3, executeJavaScri

Flowise is a drag & drop user interface to build a customized large language model flow. Prior to 3.1.3, executeJavaScriptCode() accepted caller-provided nodeVMOptions and merged them over the default...

large language model
9.4
CVSS
3 days ago
Critical nvd

CVE-2026-69253: Flowise is a drag-and-drop user interface for building customized large language model (LLM) flows. Prior to version 3.1

Flowise is a drag-and-drop user interface for building customized large language model (LLM) flows. Prior to version 3.1.3, several custom-tool components — AgentAsTool, ChatflowTool, and ExecuteFlow...

Remote Code Execution large language model llm
9.0
CVSS
3 days ago
Critical github

Flowise RCE via SQLite Record Manager Node

============================================================================= Security Advisory...

0.0
CVSS
3 days ago
Critical github

Flowise: Remote Code Execution Vulnerability in CSVAgent

### Summary The CSVAgent node was observed to allow users to write Python code which gets executed via `pyodide`. The original intent was to allow users to utilise the `pandas` library for CSV proces...

0.0
CVSS
3 days ago
Critical github

Flowise: CSV Agent Remote Code Execution via Pyodide Code Injection — Root Shell Verified

## UPDATE 2026-05-20: Full RCE as root VERIFIED **This is not theoretical — a Meterpreter reverse shell session as root has been established on Flowise 3.1.2.** ### Verified Exploit Chain 1. Python...

Remote Code Execution claude code claude llm
0.0
CVSS
3 days ago
Critical nvd

CVE-2026-69251: Flowise is a drag & drop user interface to build a customized large language model flow. Prior to 3.1.3, Flowise record

Flowise is a drag & drop user interface to build a customized large language model flow. Prior to 3.1.3, Flowise record manager and agent memory nodes allowed users to set arbitrary TypeORM DataSource...

large language model
9.0
CVSS
3 days ago
Critical github

Flowise Sandbox Escape to RCE

============================================================================= Security Advisory...

Remote Code Execution Agentic / MCP large language model function calling openai gpt-4 gpt-5 groq llm
0.0
CVSS
3 days ago
Critical github

Flowise RCE via TypeORM DataSource

============================================================================= Security Advisory...

0.0
CVSS
3 days ago
Critical nvd

CVE-2026-67598: Emlog Pro through 2.6.23 contains a disabled TLS certificate validation vulnerability in include/service/ai.php that all

Emlog Pro through 2.6.23 contains a disabled TLS certificate validation vulnerability in include/service/ai.php that allows network-adjacent attackers to intercept outbound HTTPS requests to configure...

llm
9.1
CVSS
4 days ago