CVE-2026-70477

Flowise CSV Agent prompt injection leads to remote code execution. In Flowise prior to 3.1.3, the CSV_Agents.run method uses untrusted data to build an LLM prompt, and the resulting pythonCode is executed after a validation step, which can bypass safeguards and run arbitrary code in the service a...

CVE-2026-18733

A prompt injection vulnerability in the shell tool in Amazon Strands Agents Tools before 0.8.0 might allow remote actors to execute arbitrary operating system commands on the agent's host via a crafted prompt that sets the noninteractive parameter to true, bypassing the human consent gate. To...

EUVD-2026-52432

A prompt injection vulnerability in the shell tool in Amazon Strands Agents Tools before 0.8.0 might allow remote actors to execute arbitrary operating system commands on the agent's host via a crafted prompt that sets the noninteractive parameter to true, bypassing the human consent gate. To...

CVE-2026-18733 Prompt injection bypasses shell tool consent gate in Strands Agents Tools

A prompt injection vulnerability in the shell tool in Amazon Strands Agents Tools before 0.8.0 might allow remote actors to execute arbitrary operating system commands on the agent's host via a crafted prompt that sets the noninteractive parameter to true, bypassing the human consent gate. To...

CVE-2026-18733

A prompt injection vulnerability in the shell tool in Amazon Strands Agents Tools before 0.8.0 might allow remote actors to execute arbitrary operating system commands on the agent's host via a crafted prompt that sets the noninteractive parameter to true, bypassing the human consent gate. To...

CVE-2026-18733

CVE-2026-18733 affects the Shell tool in Amazon Strands Agents Tools prior to v0.8.0. A crafted prompt can set non_interactive to true, bypassing the consent gate and potentially allowing remote execution of arbitrary OS commands on the agent host. Impact appears to involve remote command executi...

CVE-2026-18655

Improper restriction of intended endpoints in the RabbitMQ broker connection tools of the Amazon MQ MCP Server awslabs.amazon-mq-mcp-server before 2.0.24 may allow a remote unauthenticated actor via prompt injection to obtain Amazon MQ for RabbitMQ broker credentials or OAuth access tokens sent t...

CVE-2026-18655 Broker Credential and OAuth Token Disclosure in AWS Labs Amazon MQ MCP Server via Prompt Injection

Improper restriction of intended endpoints in the RabbitMQ broker connection tools of the Amazon MQ MCP Server awslabs.amazon-mq-mcp-server before 2.0.24 may allow a remote unauthenticated actor via prompt injection to obtain Amazon MQ for RabbitMQ broker credentials or OAuth access tokens sent t...

CVE-2026-18655

CVE-2026-18655 affects awslabs.amazon-mq-mcp-server (MCP) prior to 2.0.24. The issue is an improper restriction of endpoints in the RabbitMQ broker connection tools, allowing a remote unauthenticated actor (via prompt injection) to obtain Amazon MQ for RabbitMQ broker credentials or OAuth access ...

CVE-2026-18655 Broker Credential and OAuth Token Disclosure in AWS Labs Amazon MQ MCP Server via Prompt Injection

Improper restriction of intended endpoints in the RabbitMQ broker connection tools of the Amazon MQ MCP Server awslabs.amazon-mq-mcp-server before 2.0.24 may allow a remote unauthenticated actor via prompt injection to obtain Amazon MQ for RabbitMQ broker credentials or OAuth access tokens sent t...

EUVD-2026-52406

Improper restriction of intended endpoints in the RabbitMQ broker connection tools of the Amazon MQ MCP Server awslabs.amazon-mq-mcp-server before 2.0.24 may allow a remote unauthenticated actor via prompt injection to obtain Amazon MQ for RabbitMQ broker credentials or OAuth access tokens sent t...

CVE-2026-18718

Ghidra contains an ARBITRARY CODE EXECUTION vulnerability in the Swift demangler analyzer. By supplying a malicious Ghidra project with a crafted Swift tool directory path, an attacker can cause SwiftDemanglerAnalyzer to restore a persisted Swift binary directory from project state and trigger Sw...

PT-2026-67502

A prompt injection vulnerability in the shell tool in Amazon Strands Agents Tools before 0.8.0 might allow remote actors to execute arbitrary operating system commands on the agent's host via a crafted prompt that sets the non interactive parameter to true, bypassing the human consent gate. To...

Anthropic’s Opus 5 Is Better at Resisting Prompt Injection

The chart is interesting. On the IPI benchmark, Opus 5 improved over Opus 4.8, reducing the probability of an attacker succeeding within 15 attempts from 5.5% to 2.0%, and from 0.5% to 0.2% on 1 attempt. It also improved on Sonnet 5 5.9% at k=15 and Mythos 5 2.6%, making it the most robust model...

Exploit for CVE-2026-17351

CVE-2026-17351 — pgAdmin 4 AI Assistant Read-Only Bypass via L...

CVE-2026-17351

The CVE-2026-17351 issue affects pgAdmin 4 (versions from 9.13 up to, but not including, 9.17). The vulnerability stems from a mismatch between sqlparse’s string-literal handling and PostgreSQL’s parser, which can allow an LLM-supplied query executed inside a BEGIN TRANSACTION READ ONLY wrapper t...

CVE-2026-56673 ComfyUI: Path traversal in LoadImage via the /prompt API allows arbitrary file existence probing and image exfiltration

ComfyUI is a modular diffusion model GUI, API, and backend with a graph-and-node interface. Prior to 0.28.0, folderpaths.getannotatedfilepath and existsannotatedfilepath join workflow-controlled annotated filenames to a base directory without a containment check, allowing an unauthenticated craft...

CVE-2026-56673

ComfyUI is a modular diffusion model GUI, API, and backend with a graph-and-node interface. Prior to 0.28.0, folderpaths.getannotatedfilepath and existsannotatedfilepath join workflow-controlled annotated filenames to a base directory without a containment check, allowing an unauthenticated craft...

CVE-2026-56673 ComfyUI: Path traversal in LoadImage via the /prompt API allows arbitrary file existence probing and image exfiltration

ComfyUI is a modular diffusion model GUI, API, and backend with a graph-and-node interface. Prior to 0.28.0, folderpaths.getannotatedfilepath and existsannotatedfilepath join workflow-controlled annotated filenames to a base directory without a containment check, allowing an unauthenticated craft...

CVE-2026-56673

ComfyUI (multiple nodes: LoadImage, LoadImageMask, LoadImageOutput, LoadAudio, LoadLatent, LoadVideo, Load3D) suffers a path traversal in pre-0.28.0 builds where folder_paths.get_annotated_filepath and exists_annotated_filepath join workflow-controlled annotated filenames to a base directory with...