PT-2026-55082

This module enables you to test and run AI-driven workflows interactively through a chat interface. The module doesn't sufficiently enforce permissions on certain endpoints. Attackers may be able to trigger workflow execution incurring LLM spend and tool side effects or send messages into other...

Cognitive Firewall: A Proactive, Zero-Trust, Multi-Gate Framework for LLM Safety

Large language models LLMs can be induced to produce harmful content through multi turn strategies in which no single user message appears clearly unsafe. Existing runtime safeguards commonly evaluate prompts or responses as isolated messages, which limits their ability to recover ac-cumulated...

Rise from the Ashes: LLM-Based Static Analysis for Deep Learning Framework Bugs

Deep learning DL frameworks are critical AI infrastructures that often hide bugs with serious security implications. While dynamic approaches such as fuzzing are effective in uncovering these bugs, they require real test execution and incur high computational costs. Static analysis is a natural...

📄 Flowise CSV Agent Prompt Injection Remote Code Execution

This vulnerability allows remote attackers to execute arbitrary code on affected installations of FlowiseAI Flowise. Authentication is not required to exploit this vulnerability. The specific flaw exists within the run method of the CSVAgents class. The issue results from the lack of proper...

CVE-2026-58446

Presenton before 0.8.8-beta bundles an MCP server that, on server/Docker deployments configured with session authentication AUTHUSERNAME/AUTHPASSWORD, is reachable unauthenticated at /mcp because the nginx front-end does not apply the authrequest gate to that path and the MCP server auto-mints a...

282 iOS AI Apps Leak API Keys and Open AI Proxy Access in Network Traffic Study

Researchers tested 444 AI chatbot apps for iPhone and found that 282 of them, nearly two-thirds, exposed paid AI access through their network traffic. In many cases, the path in was visible just by watching what the app sent: a plaintext API key, a reusable token, or a backend server that accepte...

PT-2026-53995

Presenton before 0.8.8-beta bundles an MCP server that, on server/Docker deployments configured with session authentication AUTH USERNAME/AUTH PASSWORD, is reachable unauthenticated at /mcp because the nginx front-end does not apply the auth request gate to that path and the MCP server auto-mints...

PYSEC-2026-478 PraisonAI's unauthenticated A2A official example can reach real LLM-driven `eval()` tool execution

Summary The first-party PraisonAI A2A server example combines three behaviors into a remotely exploitable Critical chain: 1. The example exposes an A2A server without configuring authtoken. 2. The same example binds the server to 0.0.0.0. 3. The example registers a calculateexpression tool...

PYSEC-2026-461 PraisonAI Vulnerable to OS Command Injection

The executecommand function and workflow shell execution are exposed to user-controlled input via agent workflows, YAML definitions, and LLM-generated tool calls, allowing attackers to inject arbitrary shell commands through shell metacharacters. --- Description PraisonAI's workflow system and...

vanna vulnerable to remote code execution caused by prompt injection

In the latest version of vanna-ai/vanna, the vanna.ask function is vulnerable to remote code execution due to prompt injection. The root cause is the lack of a sandbox when executing LLM-generated code, allowing an attacker to manipulate the code executed by the exec function in...

Beyond Wireless Security: Covert Communications in Large Language Model-Enabled Edge Networks

Large language model LLM-enabled edge networks LLMENs offer mobile users high-quality and low-latency AI-generated content services in the 6G era. However, unlike typical edge networks, LLMENs present unique security challenges due to the inherent complexity of LLMs, their high computational...

PT-2026-53631

In the latest version of vanna-ai/vanna, the vanna.ask function is vulnerable to remote code execution due to prompt injection. The root cause is the lack of a sandbox when executing LLM-generated code, allowing an attacker to manipulate the code executed by the exec function in...

PT-2026-53484

The llm CLI tool thru 0.27.1 contains a critical code injection vulnerability via its --functions command-line argument. This argument is intended to allow users to provide custom Python function definitions. However, the tool directly executes the provided code using the unsafe exec function...

CVE-2026-54235

A flaw was found in vLLM, an inference and serving engine for large language models LLMs. The temperature validation gates, which use comparison operators, incorrectly handle Not-a-Number NaN and positive Infinity values in Python's IEEE 754 float semantics. These invalid values can bypass...

cerberus-redteam

Agent Autonome de Red Teaming Guidé par LLM et MITRE ATT&CK...

PT-2026-52167

Name of the Vulnerable Software and Affected Versions Drupal AI versions 0.0.0 through 1.2.17 Drupal AI versions 1.3.0 through 1.3.8 Drupal AI versions 1.4.0 through 1.4.3 Description Improper neutralization of input during web page generation allows Cross-Site Scripting XSS. The module and...

CVE-2026-45792

rtk filters and compresses command outputs before they reach your LLM context. Prior to 0.32.0, RTK Rust Token Killer improperly trusts project-local configuration files. RTK automatically loads .rtk/filters.toml from the working directory with highest priority and without user notification. An...

CVE-2026-45792 RTK improperly trusts project-local filter configuration, allowing silent tampering of command output shown to LLM

rtk filters and compresses command outputs before they reach your LLM context. Prior to 0.32.0, RTK Rust Token Killer improperly trusts project-local configuration files. RTK automatically loads .rtk/filters.toml from the working directory with highest priority and without user notification. An...

PYSEC-2026-242

Langflow is a tool for building and deploying AI-powered agents and workflows. Prior to 1.9.0, Langflow's /api/v1/monitor router exposes 7 endpoints that perform read, write, and delete operations on user-owned resources — messages, sessions, build artifacts, and LLM transaction logs — without...

PT-2026-51583

Name of the Vulnerable Software and Affected Versions rtk versions prior to 0.42.2 Description A flaw in the permission splitter logic fails to conservatively split or reject certain Bash shell constructs that create command-execution boundaries or nested execution. This improper input validation...