9router: Unauthenticated `/v1` proxy access via `Host`-header spoofing → open AI relay + SSRF

Summary 9router's request guard decides a request is "local" and therefore exempt from API-key auth on the /v1 LLM proxy by reading the client-controlled Host header. Because 9router binds 0.0.0.0 by default and the CLI misleadingly prints "localhost", a remote, unauthenticated attacker who can...

9router: Unauthenticated LLM proxy access via /codex rewrite authorization bypass

Summary 9router exposes an OpenAI/Anthropic-compatible LLM proxy. Remote access to this proxy is intended to be protected by an API-key check in the Next.js middleware. However, 9router also defines a rewrite that maps /codex/ to the backend LLM endpoint /api/v1/responses. The middleware...

NPM: 9router: Unauthenticated LLM proxy access via /codex rewrite authorization bypass

NPM: 9router: Unauthenticated LLM proxy access via /codex rewrite authorization bypass vulnerability discovered by ? in WordPress Npm 9router versions 0.5.2...

GHSA-8GMQ-J984-VP4R 9router: Unauthenticated LLM proxy access via /codex rewrite authorization bypass

Summary 9router exposes an OpenAI/Anthropic-compatible LLM proxy. Remote access to this proxy is intended to be protected by an API-key check in the Next.js middleware. However, 9router also defines a rewrite that maps /codex/ to the backend LLM endpoint /api/v1/responses. The middleware...

EUVD-2026-67846

Improper neutralization of input used for llm prompting in Microsoft Edge for iOS allows an unauthorized attacker to perform spoofing over a network...

Microsoft Edge for iOS Spoofing Vulnerability

Improper neutralization of input used for llm prompting in Microsoft Edge for iOS allows an unauthorized attacker to perform spoofing over a network...

BEACON: Behavior-Anchored Cross-Source Knowledge Graph Construction for Cyber Threat Intelligence

Cyber threat intelligence CTI is foundational to modern cyber defense, yet much of it resides in unstructured reports whose volume and heterogeneity far exceed manual analysis, motivating research on automatically constructing knowledge graphs from CTI reports. However, existing approaches mainly...

LLM-Based Agents for Software and Systems Security: Approaches, Applications, and Assessment

Software and systems security workflows are typically procedural: analysts inspect heterogeneous artifacts, form hypotheses, invoke tools, interpret outputs, and revise plans. Large language model LLM-based agents, which can plan, use tools, retain state, and revise actions across multi-step...

Compared to What? A Human-Anchored Security Benchmark for LLM-Generated Infrastructure-As-Code

Large language models are increasingly used to author Infrastructure-as-Code IaC, where a single insecure default can be deployed directly into production. Prior evaluations report raw vulnerability counts for model-generated IaC, but without a human baseline they cannot determine whether models...

CVE-2026-70331: Undefined Security Weakness

Improper neutralization of input used for llm prompting in Microsoft Edge for iOS allows an unauthorized attacker to perform spoofing over a network...

9router: Unauthenticated LLM proxy access via /codex rewrite authorization bypass

9router exposes an OpenAI/Anthropic-compatible LLM proxy. Remote access to this proxy is intended to be protected by an API-key check in the Next.js middleware. However, 9router also defines a rewrite that maps /codex/ to the backend LLM endpoint /api/v1/responses. The middleware authorization...

CAITLYN: Can LLM Agents Autonomously Synthesize Defenses against Emerging Injection Attacks?

Prompt injection attacks on Large Language Model LLM agents seek to introduce malicious instructions or content into external text sources retrieved by agents, forcing the underlying LLMs to execute harmful actions outside their benign scope. While current defenses effectively counter known...

PT-2026-83265

Name of the Vulnerable Software and Affected Versions Microsoft Edge for iOS affected versions not specified Description Improper neutralization of input used for Large Language Model LLM prompting allows an unauthorized attacker to perform spoofing over a network. LLM prompting refers to the...

LongPIBench: A Long-Context Benchmark for Prompt Injection

Prompt injection attacks pose a serious security risk to large language models in real-world applications. However, existing prompt injection benchmarks primarily focus on short-context inputs, leaving the attacks and defenses in long-context settings largely unexplored. This gap leads to a...

When Verified Source Becomes Attack Input: Defending Smart Contracts against LLM-Based Vulnerability Scanning

Smart contracts are financial programs deployed on blockchains to manage digital assets. To build trust with users and investors, smart contract projects typically publish their source code on blockchain explorers and verify it against the deployed bytecode, making the on-chain program accessible...

TagZilla: Automated Owner and Abuse Type Tagging for Indicators of Compromise in Threat Reports

Cyber Threat Intelligence CTI reports often describe Indicators of Compromise IoCs such as IP addresses, URLs, file hashes, and cryptocurrency wallets involved in cyberattacks. Those IoCs are typically described in the unstructured report's text, or listed at the end of the report with little...

Breaking Darknet CAPTCHAs with General Purpose LLM

Our work evaluates the effectiveness of automated methods for solving CAPTCHA challenges commonly encountered in darknet environments. These CAPTCHAs are typically designed to operate without JavaScript, resulting in distinct characteristics compared to mainstream CAPTCHA systems. Our study...

“Sorry, I can’t help with that”: How your guardrails might become the attacker’s best friend

Welcome to this week's edition of the Threat Source newsletter. Hello, everyone. Long time reader, first time writer here at the Threat Source newsletter! I wanted to start out by introducing myself. My colleague and friend Mick Baccio set the bar pretty high last week, so I was planning to tell...

SkillSpector v2.10.0

SkillSpector Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, and security risks before installing agent skills. Overview AI agent skills used by Claude Code, Codex CLI, Gemini CLI, etc. execute with implicit trust and minimal vetting. Research shows that 26.1% of...

promptfoo v0.122.1

Promptfoo: LLM evals & red teaming promptfoo is a CLI and library for evaluating and red-teaming LLM apps. Stop the trial-and-error approach - start shipping secure, reliable AI apps. Website · Getting Started · Red Teaming · Documentation · Discord Promptfoo is now part of OpenAI. Promptfoo...