This archive includes all published incident pages. Page 17 of 55.
Each page is intended to help a security team answer three questions quickly: why the issue is AI-relevant, what part of the workflow may be exposed, and what actions should happen first.
Selection criteria and correction policy are documented in Methodology & Editorial Policy.
Source disclosure: August 11, 2026 | Published on Radar: October 13, 2026
n8n versions before 2.32.1 fail to enforce the Allowed HTTP Request Domains allowlist in multiple AI and LLM nodes when user-supplied base or endpoint URLs are configured.
Source disclosure: August 10, 2026 | Published on Radar: October 13, 2026
Firecrawl turns entire websites into LLM-ready markdown or structured data. Prior to 2.11.32, a critical arbitrary file read vulnerability exists in Firecrawl's extraction functionality due to unsafe schema dereferencing of user-supplied...
Source disclosure: August 7, 2026 | Published on Radar: October 13, 2026
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 unauthenticated network attacker to read...
Source disclosure: August 6, 2026 | Published on Radar: October 13, 2026
Insecure direct object reference in the mongodb memory, elasticsearch memory, and mem0 memory tools in Amazon Strands Agents Tools before 0.8.
Source disclosure: August 6, 2026 | Published on Radar: October 13, 2026
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(), and because Zod v4 defines zod as a...
Source disclosure: August 5, 2026 | Published on Radar: October 13, 2026
IBM Langflow OSS 1.0.0 through 1.10.3 could allow an authenticated attacker to execute unintended code during Agentic Assistant validation due to improper handling of LLM‑generated components.
Source disclosure: August 4, 2026 | Published on Radar: October 13, 2026
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 a malicious Python script that...
Source disclosure: August 4, 2026 | Published on Radar: October 13, 2026
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-controlled CSV data with file.split(',').
Source disclosure: August 3, 2026 | Published on Radar: October 13, 2026
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...
Source disclosure: August 3, 2026 | Published on Radar: October 13, 2026
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 configured LLM providers by presenting...