VulnWatch VulnWatch

AI Security Dashboard

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

Total Entries
1,333
Critical
140
Actively Exploited
6
Last 24h
17

Get the weekly digest

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

Critical nvd

CVE-2024-58351: Flowise before 2.1.4 allows configuration to be injected into the Chainflow during execution via the overrideConfig opti

Flowise before 2.1.4 allows configuration to be injected into the Chainflow during execution via the overrideConfig option, supported in both the frontend web integration and the backend Prediction AP...

9.3
CVSS
3 hours ago
Critical github

Langflow: BaseFileComponent-based nodes arbitrary file read with RCE exploit

### Summary All components based on `BaseFileComponent` are vulnerable to the following vulnerability: 1. Docling (`DoclingInlineComponent`) 2. Docling Serve (`DoclingRemoteComponent`) 3. Read File (`...

Remote Code Execution vector database langflow chroma
9.6
CVSS
22 hours ago
Critical github

Langflow: IDOR Vulnerability in `/api/v1/responses` Endpoint Allows Authenticated Attackers to Access Another User's Flow

## Summary Insecure Direct Object Reference (IDOR) vulnerability in `/api/v1/responses` endpoint allows an authenticated attacker to execute any flow belonging to another user by specifying the victi...

langflow openai
9.9
CVSS
22 hours ago
Critical github

Network-AI: CVE-2026-46701 fix incomplete — empty default secret still authorizes all requests

## Advisory / Disclosure # Network-AI — CVE-2026-46701 fix is incomplete: the "Empty Default Secret" unauth path survives **Target:** Jovancoding/Network-AI (npm `network-ai`), **latest v5.7.1** **S...

9.1
CVSS
1 day ago
Critical nvd

CVE-2026-12048: Stored cross-site scripting in pgAdmin 4's error-rendering and plan-node-rendering paths. Text returned by a PostgreSQL

Stored cross-site scripting in pgAdmin 4's error-rendering and plan-node-rendering paths. Text returned by a PostgreSQL server (ErrorResponse messages, including object names quoted back inside relati...

llm
9.3
CVSS
1 day ago
Critical nvd

CVE-2026-12045: Read-only transaction bypass in the pgAdmin 4 AI Assistant allows an attacker who can influence database content that th

Read-only transaction bypass in the pgAdmin 4 AI Assistant allows an attacker who can influence database content that the assistant reads to execute arbitrary SQL with the privileges of the pgAdmin us...

9.4
CVSS
1 day ago
Critical nvd

CVE-2026-54130: Missing authentication for critical function in M365 Copilot allows an unauthorized attacker to disclose information ove

Missing authentication for critical function in M365 Copilot allows an unauthorized attacker to disclose information over a network.

copilot
9.8
CVSS
1 day ago
Critical nvd

CVE-2026-49257: mcp-pinot is a Python-based Model Context Protocol (MCP) server for interacting with Apache Pinot. In versions 3.0.1 and

mcp-pinot is a Python-based Model Context Protocol (MCP) server for interacting with Apache Pinot. In versions 3.0.1 and below, mcp-pinot defaults to running an HTTP MCP server bound to 0.0.0.0:8080 w...

Agentic / MCP model context protocol mcp server
10.0
CVSS
1 day ago
Critical github

gemini-mcp-tool vulnerable to OS command injection and @file exfiltration via prompt quoting (CVE-2026-0755)

Untrusted prompt input could reach the Gemini CLI @file parser, allowing read/exfiltration of arbitrary local files (@/etc/passwd, @~/.ssh/id_rsa, @../../secret). On Windows, unquoted cmd.exe metachar...

9.8
CVSS
1 day ago
Critical github

praisonai-platform: default JWT signing secret 'dev-secret-change-me' enables token forgery

# praisonai-platform: default JWT signing secret `dev-secret-change-me` **Researcher:** Kai Aizen — SnailSploit (@SnailSploit), Adversarial & Offensive Security Research **Target:** https://github.co...

adversarial
9.8
CVSS
2 days ago
Critical github

PraisonAI: Arbitrary File Read/Write via `multiedit` Tool Without Path Validation

## Summary The `multiedit` tool in `src/praisonai/praisonai/tools/multiedit.py` allows LLM-controlled arbitrary file read and write without any path validation, workspace boundary check, or protected...

9.1
CVSS
2 days ago
Critical github

npm PraisonAI MCPServer exposes unauthenticated HTTP tools/call

## Summary The published npm package `praisonai` exports a TypeScript `MCPServer` that can expose tools, resources, and prompts over an HTTP JSON-RPC transport with: ```ts await server.start({ port:...

9.8
CVSS
2 days ago
Critical github

npm PraisonAI AgentOS exposes unauthenticated agent listing and invocation

## Summary The published npm package `praisonai` ships a TypeScript `AgentOS` HTTP server that defaults to `host: "0.0.0.0"` and registers sensitive agent routes without any authentication or authori...

9.4
CVSS
2 days ago
Critical github

PraisonAI: Remote Code Execution via Sandbox Escape in `codeMode` Tool

## Summary The `codeMode` tool in `src/praisonai-ts/src/tools/builtins/code-mode.ts` uses `new Function()` with a `with(sandbox)` pattern to execute LLM-generated code. The blocklist-based "sandbox"...

9.8
CVSS
2 days ago
Critical github

npm PraisonAI codeMode sandbox escape via Function constructor

## Summary The published npm package `praisonai` exports a TypeScript built-in tool named `codeMode`. The package describes this tool as executing code in a sandboxed environment, marks its capabilit...

llm
9.9
CVSS
2 days ago
Critical github

PraisonAI: Missing Authentication for Critical Function and Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection') in praisonai

# Unauthenticated PraisonAI UI MCP connect endpoint executes attacker-chosen local commands ## Summary PraisonAI v4.6.48 exposes the PraisonAIUI MCP client management API through the default UI host...

9.8
CVSS
2 days ago
Critical github

PraisonAI: AgentOS remains unauthenticated after incomplete fix version and allows remote agent invocation

# AgentOS remains unauthenticated after GHSA-pm96 patched version and allows remote agent invocation ## Summary PraisonAI's `AgentOS` FastAPI deployment surface remains unauthenticated in current ma...

llm
9.8
CVSS
2 days ago
Critical github

PraisonAI AgentTeam.launch exposes unauthenticated remote agent listing and invocation endpoints

# PraisonAI `AgentTeam.launch()` exposes unauthenticated remote agent invocation endpoints ## Summary PraisonAI's documented Python `AgentTeam.launch()` / `Agents.launch()` HTTP server starts extern...

9.8
CVSS
2 days ago
Critical github

PraisonAI: Jobs API exposes agent-execution endpoints with no authentication

# praisonai: Jobs API exposes agent-execution endpoints with no authentication **Researcher:** Kai Aizen — SnailSploit (@SnailSploit), Adversarial & Offensive Security Research **Target:** https://g...

Remote Code Execution SSRF adversarial anthropic autogen crewai openai llm
9.8
CVSS
2 days ago
Critical github

praisonai: recipe serve auth middleware silently disables itself when no secret is set

# praisonai: `recipe serve` authentication middleware silently disables itself when no secret is set **Researcher:** Kai Aizen — SnailSploit (@SnailSploit), Adversarial & Offensive Security Research...

9.8
CVSS
2 days ago
Critical github

PraisonAI: Unauthenticated RCE via Jobs API + Approval Bypass

# Unauthenticated Remote Code Execution via Jobs API and Approval Bypass in PraisonAI ## Summary An unauthenticated attacker can execute arbitrary OS commands on any server running the PraisonAI J...

9.8
CVSS
2 days ago
Critical nvd

CVE-2026-48814: Network-AI is a TypeScript/Node.js multi-agent orchestrator. In versions 5.7.1 and earlier, the MCP SSE server allows un

Network-AI is a TypeScript/Node.js multi-agent orchestrator. In versions 5.7.1 and earlier, the MCP SSE server allows unauthenticated cross-origin MCP tool invocation due to an empty default secret. T...

9.1
CVSS
2 days ago
Critical github

Langflow: Unauthenticated file upload leads to DoS (space exhaustion) and information leak

### Summary Unauthenticated users can upload any amount of data to the server without any limitations. No need for any prior knowledge, only network access to Langflow. This can lead to space exhaust...

langflow
9.3
CVSS
3 days ago
Critical nvd

CVE-2026-55743: The shell tool command allowlist in the SecurityPolicy of OpenHuman desktop agent through 0.54.0 (default Supervised sec

The shell tool command allowlist in the SecurityPolicy of OpenHuman desktop agent through 0.54.0 (default Supervised security policy) can be bypassed to execute arbitrary OS commands with the privileg...

Prompt Injection Remote Code Execution prompt injection indirect prompt llm
9.4
CVSS
3 days ago
Critical nvd

CVE-2026-48797: Backpropagate is a Python library for fine-tuning large language models on a single GPU. In versions 1.1.0 and 1.1.1, th

Backpropagate is a Python library for fine-tuning large language models on a single GPU. In versions 1.1.0 and 1.1.1, the optional Reflex web UI exposes a training control plane without authentication...

large language model huggingface
9.3
CVSS
3 days ago