Model Security Is the Wrong Frame – The Real Risk Is Workflow Security

As AI copilots and assistants become embedded in daily work, security teams are still focused on protecting the models themselves. But recent incidents suggest the bigger risk lies elsewhere: in the workflows that surround those models. Two Chrome extensions posing as AI helpers were recently...

Agent Skills in the Wild: An Empirical Study of Security Vulnerabilities at Scale

The rise of AI agent frameworks has introduced agent skills, modular packages containing instructions and executable code that dynamically extend agent capabilities. While this architecture enables powerful customization, skills execute with implicit trust and minimal vetting, creating a...

CVE-2026-22708

Cursor is a code editor built for programming with AI. Prior to 2.3, hen the Cursor Agent is running in Auto-Run Mode with Allowlist mode enabled, certain shell built-ins can still be executed without appearing in the allowlist and without requiring user approval. This allows an attacker via...

CVE-2026-22708 Cursor has a Terminal Tool Allowlist Bypass via Environment Variables

Cursor is a code editor built for programming with AI. Prior to 2.3, hen the Cursor Agent is running in Auto-Run Mode with Allowlist mode enabled, certain shell built-ins can still be executed without appearing in the allowlist and without requiring user approval. This allows an attacker via...

EUVD-2026-2678

Cursor is a code editor built for programming with AI. Prior to 2.3, hen the Cursor Agent is running in Auto-Run Mode with Allowlist mode enabled, certain shell built-ins can still be executed without appearing in the allowlist and without requiring user approval. This allows an attacker via...

CVE-2026-22708 Cursor has a Terminal Tool Allowlist Bypass via Environment Variables

Cursor is a code editor built for programming with AI. Prior to 2.3, hen the Cursor Agent is running in Auto-Run Mode with Allowlist mode enabled, certain shell built-ins can still be executed without appearing in the allowlist and without requiring user approval. This allows an attacker via...

CVE-2026-22708

Cursor is a code editor built for programming with AI. Prior to 2.3, hen the Cursor Agent is running in Auto-Run Mode with Allowlist mode enabled, certain shell built-ins can still be executed without appearing in the allowlist and without requiring user approval. This allows an attacker via...

The Promptware Kill Chain: How Prompt Injections Gradually Evolved into a Multi-Step Malware

Whitepaper called The Promptware Kill Chain: How Prompt Injections Gradually Evolved Into A Multi-Step Malware...

CVE-2026-22708: External Control of System or Configuration Setting

Cursor is a code editor built for programming with AI. Prior to 2.3, hen the Cursor Agent is running in Auto-Run Mode with Allowlist mode enabled, certain shell built-ins can still be executed without appearing in the allowlist and without requiring user approval. This allows an attacker via...

PT-2026-2918

Name of the Vulnerable Software and Affected Versions Cursor versions prior to 2.3 Description Cursor is a code editor designed for programming with AI. When the Cursor Agent operates in Auto-Run Mode with Allowlist mode enabled, certain shell built-ins can be executed without appearing on the...

Cursor 安全漏洞

Cursor is a Cursor open source intelligent code editor with deep AI integration. A security vulnerability exists in versions prior to Cursor 2.3 that stems from the fact that in autorun mode, certain shell built-in commands can be executed without being whitelisted and without the need for user...

CVE-2024-58340

LangChain versions up to and including 0.3.1 contain a regular expression denial-of-service ReDoS vulnerability in the MRKLOutputParser.parse method libs/langchain/langchain/agents/mrkl/outputparser.py. The parser applies a backtracking-prone regular expression when extracting tool actions from...

CVE-2026-22687

WeKnora is an LLM-powered framework designed for deep document understanding and semantic retrieval. Prior to version 0.2.5, after WeKnora enables the Agent service, it allows users to call the database query tool. Due to insufficient backend validation, an attacker can use prompt‑based bypass...

PYSEC-2026-75

LangChain versions up to and including 0.3.1 contain a regular expression denial-of-service ReDoS vulnerability in the MRKLOutputParser.parse method libs/langchain/langchain/agents/mrkl/outputparser.py. The parser applies a backtracking-prone regular expression when extracting tool actions from...

PYSEC-2026-86

LlamaIndex run-llama/llamaindex versions up to and including 0.12.2 contain an uncontrolled resource consumption vulnerability in the VannaPack VannaQueryEngine implementation. The customquery logic generates SQL statements from a user-supplied prompt and executes them via vn.runsql without...

CVE-2024-58340 LangChain <= 0.3.1 MRKLOutputParser ReDoS

LangChain versions up to and including 0.3.1 contain a regular expression denial-of-service ReDoS vulnerability in the MRKLOutputParser.parse method libs/langchain/langchain/agents/mrkl/outputparser.py. The parser applies a backtracking-prone regular expression when extracting tool actions from...

CVE-2024-58340

LangChain

⚡ Weekly Recap: AI Automation Exploits, Telecom Espionage, Prompt Poaching & More

This week made one thing clear: small oversights can spiral fast. Tools meant to save time and reduce friction turned into easy entry points once basic safeguards were ignored. Attackers didn't need novel tricks. They used what was already exposed and moved in without resistance. Scale amplified...

CVE-2024-58340: Inefficient Regular Expression Complexity

LangChain versions up to and including 0.3.1 contain a regular expression denial-of-service ReDoS vulnerability in the MRKLOutputParser.parse method libs/langchain/langchain/agents/mrkl/outputparser.py. The parser applies a backtracking-prone regular expression when extracting tool actions from...

CVE-2026-22687

WeKnora is an LLM-powered framework designed for deep document understanding and semantic retrieval. Prior to version 0.2.5, after WeKnora enables the Agent service, it allows users to call the database query tool. Due to insufficient backend validation, an attacker can use prompt‑based bypass...