CVE-2026-15077

GitLab has remediated an issue in GitLab EE affecting all versions from 19.1 before 19.1.3 and 19.2 before 19.2.1 that under certain conditions could have allowed an authenticated user to access information from unauthorized projects due to improper neutralization of untrusted content processed b...

CVE-2026-15077

GitLab EE is affected in CVE-2026-15077 by improper neutralization of untrusted content processed during AI-assisted code review. The issue could allow an authenticated user to access information from unauthorized projects under certain conditions. Affected versions are all 19.1 prior to 19.1.3 a...

Understanding the Impact of AI Code Assistants on Security API Usage: An Empirical Study

AI code assistants are transforming software development, but their implications for software security remain a major concern, particularly in the context of security APIs. These APIs are critical for safeguarding software systems, yet their complexity often leads to incorrect use and serious...

ai-code-review (>=2.0.0.dev1, <=3.1.2), ai-cr (>=2.0.0.dev1, <=3.1.2) +23 more potentially affected by CVE-2026-32871 via fastmcp (2.8.1)

fastmcp PYPI version 2.8.1 is affected by a known vulnerability. The following packages have a transitive dependency on fastmcp and may be impacted: - ai-code-review =2.0.0.dev1, =2.0.0.dev1, =4.0.0.dev21, =0.0.1, =0.2.0, =2.0.0.dev1, =0.0.1, =0.0.1, =0.0.1, =0.0.1, =0.0.1, =0.0.3 and more Source...

Unsafe Dependency Resolution

Overview @theia/ai-code-completion is a Theia - AI Core Affected versions of this package are vulnerable to Unsafe Dependency Resolution via the automatic loading of .prompts/.prompttemplate files in a workspace. An attacker can manipulate the AI agent's system instructions by introducing crafted...

@fangoling/ai-terminal-assistant (0.1.0), @theia/ai-anthropic (>=1.57.0-next.37, <=1.71.0-next.72) +28 more potentially affected by CVE-2026-46580 via @theia/ai-core (>=1.46.0-next.241, <=1.71.0-next.72)

@theia/ai-core NPM version =1.46.0-next.241, =1.57.0-next.37, =1.46.0-next.241, =1.46.0-next.241, =1.65.0, =1.46.0-next.241, =1.67.0-next.56, =1.68.0-next.79, =1.64.0, =0.0.1, =1.60.0, =1.46.0-next.241, =1.46.0-next.241, =1.59.0-next.62, =1.71.0-next.72 - @theia/ai-ide-agents 1.57.0-next.136 and...

Context-Based Adversarial Attacks on AI Code Generators: Vulnerability Analysis and Implications

AI-powered code generation systems have transformed software development but introduce critical inference-time security vulnerabilities. This research presents a systematic investigation of context-based adversarial attacks, where strategically crafted contextual inputs, including comments,...

Bringing AI Code Security into Qualys ETM

A first-class data model for the next generation of findings AI-driven code security is becoming a real category. Anthropic's Claude Code Security and OpenAI's Codex Security are the leading examples, and more will follow. These tools reason about source code at a depth that traditional SAST cann...

CVE-2026-7157

A flaw has been found in disler aider-mcp-server up to b2516fa466d0d851932da92ee6d0e66946db9efc. Affected by this vulnerability is an unknown functionality of the file src/aidermcpserver/server.py of the component aideraicode. This manipulation of the argument relativeeditablefiles causes command...

CVE-2026-7157

A flaw has been found in disler aider-mcp-server up to b2516fa466d0d851932da92ee6d0e66946db9efc. Affected by this vulnerability is an unknown functionality of the file src/aidermcpserver/server.py of the component aideraicode. This manipulation of the argument relativeeditablefiles causes command...

CVE-2026-7157 disler aider-mcp-server aider_ai_code server.py command injection

A flaw has been found in disler aider-mcp-server up to b2516fa466d0d851932da92ee6d0e66946db9efc. Affected by this vulnerability is an unknown functionality of the file src/aidermcpserver/server.py of the component aideraicode. This manipulation of the argument relativeeditablefiles causes command...

CVE-2026-7157

Affects disler aider-mcp-server (up to b2516fa466d0d851932da92ee6d0e66946db9efc) in the component aider_ai_code, specifically the file src/aider_mcp_server/server.py. The vulnerability arises from a manipulation of the argument relative_editable_files, leading to command injection. Remote exploit...

EUVD-2026-25924

A flaw has been found in disler aider-mcp-server up to b2516fa466d0d851932da92ee6d0e66946db9efc. Affected by this vulnerability is an unknown functionality of the file src/aidermcpserver/server.py of the component aideraicode. This manipulation of the argument relativeeditablefiles causes command...

VibeGuard: A Security Gate Framework for AI-Generated Code

"Vibe coding," in which developers delegate code generation to AI assistants and accept the output with little manual review, has gained rapid adoption in production settings. On March 31, 2026, Anthropic's Claude Code CLI shipped a 59.8 MB source map file in its npm package, exposing roughly...

ai-code-review (>=2.0.0.dev1, <=3.1.2), ai-cr (>=2.0.0.dev1, <=3.1.2) +23 more potentially affected by CVE-2026-27124 via fastmcp (2.8.1)

fastmcp PYPI version 2.8.1 is affected by a known vulnerability. The following packages have a transitive dependency on fastmcp and may be impacted: - ai-code-review =2.0.0.dev1, =2.0.0.dev1, =4.0.0.dev21, =0.0.1, =0.2.0, =2.0.0.dev1, =0.0.1, =0.0.1, =0.0.1, =0.0.1, =0.0.1, =0.0.3 and more Source...

CVE-2026-30304

In its design for automatic terminal command execution, AI Code offers two options: Execute safe commands and execute all commands. The description for the former states that commands determined by the model to be safe will be automatically executed, whereas if the model judges a command to be...

AI Code security vulnerabilities

AI Code is a code programming assistant developed by TianGuaDuiZhang. AI Code has a security vulnerability, which stems from the design of automatic terminal command execution, making it susceptible to prompt injection attacks, potentially allowing arbitrary command execution...

CVE-2026-30304: Improper Input Validation

In its design for automatic terminal command execution, AI Code offers two options: Execute safe commands and execute all commands. The description for the former states that commands determined by the model to be safe will be automatically executed, whereas if the model judges a command to be...

ZAST.AI Raises $6M Pre-A to Scale "Zero False Positive" AI-Powered Code Security

January 5, 2026, Seattle, USA — ZAST.AI announced the completion of a $6 million Pre-A funding round. This investment came from the well-known investment firm HH Capital, bringing ZAST.AI's total funding close to $10 million. This marks a recognition from leading capital markets of a new solution...

Breaking the Code: Security Assessment of AI Code Agents through Systematic Jailbreaking Attacks

Code-capable large language model LLM agents are increasingly embedded into software engineering workflows where they can read, write, and execute code, raising the stakes of safety-bypass "jailbreak" attacks beyond text-only settings. Prior evaluations emphasize refusal or harmful-text detection...