Persona Attack: Incremental Memory Injection Jailbreak Attack against Large Language Models

As Large Language Models evolve for user convenience, vulnerability to jailbreak attacks continues to be reported despite ongoing efforts in safety training. Traditional jailbreak techniques typically focus on a single prompt injection, neglecting the models' ability to remember the flow of...

Arbitrary Code Execution.

@anthropic-ai/claude-code is vulnerable to Arbitrary code execution. The vulnerability is due to improper parsing of shell commands involving $IFS and short CLI flags, which allows an attacker to bypass read-only validation and execute arbitrary code by injecting untrusted content into the contex...

An Agentic Multi-Agent Architecture for Cybersecurity Risk Management

Getting a real cybersecurity risk assessment for a small organization is expensive -- a NIST CSF-aligned engagement runs $15,000 on the low end, takes weeks, and depends on practitioners who are genuinely scarce. Most small companies skip it entirely. We built a six-agent AI system where each age...

Claude Code Vulnerable to Command Injection via Directory Change Bypasses Write Protection

Claude Code failed to properly validate directory changes when combined with write operations to protected folders. By using the cd command to navigate into sensitive directories like .claude, it was possible to bypass write protection and create or modify files without user confirmation. Reliabl...

CVE-2026-25722

Claude Code is an agentic coding tool. Prior to version 2.0.57, Claude Code failed to properly validate directory changes when combined with write operations to protected folders. By using the cd command to navigate into sensitive directories like .claude, it was possible to bypass write protecti...

CVE-2026-25722 Claude Code Vulnerable to Command Injection via Directory Change Bypasses Write Protection

Claude Code is an agentic coding tool. Prior to version 2.0.57, Claude Code failed to properly validate directory changes when combined with write operations to protected folders. By using the cd command to navigate into sensitive directories like .claude, it was possible to bypass write protecti...

EUVD-2026-5636

Claude Code is an agentic coding tool. Prior to version 2.0.57, Claude Code failed to properly validate directory changes when combined with write operations to protected folders. By using the cd command to navigate into sensitive directories like .claude, it was possible to bypass write protecti...

PT-2026-6763

Name of the Vulnerable Software and Affected Versions Claude Code versions prior to 2.0.57 Description Claude Code, an agentic coding tool, did not properly validate directory changes when combined with write operations to protected folders. Utilizing the cd command to navigate into sensitive...

PT-2026-6853

Claude Code failed to properly validate directory changes when combined with write operations to protected folders. By using the cd command to navigate into sensitive directories like .claude, it was possible to bypass write protection and create or modify files without user confirmation. Reliabl...

CVE-2026-24887

Claude Code is an agentic coding tool. Prior to version 2.0.72, due to an error in command parsing, it was possible to bypass the Claude Code confirmation prompt to trigger execution of untrusted commands through the find command. Reliably exploiting this required the ability to add untrusted...

CVE-2026-24887

Claude Code is an agentic coding tool. Prior to version 2.0.72, due to an error in command parsing, it was possible to bypass the Claude Code confirmation prompt to trigger execution of untrusted commands through the find command. Reliably exploiting this required the ability to add untrusted...

CVE-2026-24887

Claude Code is an agentic coding tool. Prior to version 2.0.72, due to an error in command parsing, it was possible to bypass the Claude Code confirmation prompt to trigger execution of untrusted commands through the find command. Reliably exploiting this required the ability to add untrusted...

Claude Code has a Command Injection in find Command Bypasses User Approval Prompt

Due to an error in command parsing, it was possible to bypass the Claude Code confirmation prompt to trigger execution of untrusted commands through the find command. Reliably exploiting this required the ability to add untrusted content into a Claude Code context window. Users on standard Claude...

GHSA-QGQW-H4XQ-7W8W Claude Code has a Command Injection in find Command Bypasses User Approval Prompt

Due to an error in command parsing, it was possible to bypass the Claude Code confirmation prompt to trigger execution of untrusted commands through the find command. Reliably exploiting this required the ability to add untrusted content into a Claude Code context window. Users on standard Claude...

PT-2026-6214

Name of the Vulnerable Software and Affected Versions Claude Code versions prior to 2.0.72 Description Claude Code is an agentic coding tool. A flaw in command parsing allowed bypassing the confirmation prompt, potentially triggering the execution of untrusted commands via the find command...

Spring AI Agentic Patterns (Part 4): Subagent Orchestration

Instead of one generalist agent doing everything, delegate to specialized agents. This keeps context windows focused—preventing the clutter that degrades performance. Task tool, part of the spring-ai-agent-utils toolkit, is a portable, model-agnostic Spring AI implementation inspired by Claude...

CVE-2025-66032 Claude Code Command Validation Bypass Allows Arbitrary Code Execution

Claude Code is an agentic coding tool. Prior to 1.0.93, Due to errors in parsing shell commands related to $IFS and short CLI flags, it was possible to bypass the Claude Code read-only validation and trigger arbitrary code execution. Reliably exploiting this requires the ability to add untrusted...

CVE-2025-66032

Claude Code (the agentic coding tool) is affected by a vulnerability in versions prior to 1.0.93 where errors in parsing shell commands related to $IFS and short CLI flags allow bypassing the read-only validation and may enable arbitrary code execution. Exploitation requires the attacker to intro...

From LLMs to Agents: A Comparative Evaluation of LLMs and LLM-Based Agents in Security Patch Detection

The widespread adoption of open-source software OSS has accelerated software innovation but also increased security risks due to the rapid propagation of vulnerabilities and silent patch releases. In recent years, large language models LLMs and LLM-based agents have demonstrated remarkable...

Improper Input Validation

@anthropic-ai/claude-code is vulnerable to Improper Input Validation. The vulnerability is due to an error in command parsing that allows an attacker to bypass the confirmation prompt and trigger execution of untrusted commands by injecting malicious content into a Claude Code context window...