Loading story…
Researchers examined 9,041 open-source applications built with Claude Code and Lovable, plus 200 publicly deployed applications, and identified 1,186 vulnerabilities. Their audit found that 91% of deployed applications had at least one flaw and that 65.77% of identified issues were Critical or High severity, led by broken access control, injection vulnerabilities, and authentication failures. The study attributes recurring defects to eight failure modes involving AI-agent memory, objectives, and knowledge; stronger prompts and agent harnesses reduced, but did not eliminate, exposure.
The findings align with reported failures in AI-generated applications, including CVE-2025-48757 (CVSS 9.3), where Lovable applications using Supabase could expose database tables without authentication when Row Level Security policies were absent. Organizations adopting AI coding agents should enforce human security review, automated application testing, secret scanning, least-privilege authorization, and explicit database access controls before deployment; they should also treat coding assistants and their dependencies as potential supply-chain and prompt-injection targets.
Track how attackers are adapting to this technology.
5 events from the most recent confirmed update back to the earliest known activity.
The cited version of “Understanding the (In)Security of Vibe-Coded Applications” was revised. The paper identifies broken access control, injection, and authentication failures as leading issue categories and attributes recurring weaknesses to AI-agent memory, objective, and knowledge defects.
Junquan Deng, Zhiyu Fan, and Ruijie Meng submitted a study of 9,041 open-source Claude Code and Lovable applications and an audit of 200 publicly deployed applications. The audit identified 1,186 vulnerabilities; 91.0% of audited applications had at least one vulnerability, and 65.77% of identified flaws were Critical or High severity.
A Veracode update reported in March 2026 found that the pass rate for AI-generated code remained around 55% despite improvements in code compilability.
Attacks or vulnerabilities affecting Amazon Q Developer, Cursor, and GitHub Copilot were disclosed in 2025. Reported scenarios included a misconfigured GitHub token used to inject code into an Amazon Q Developer VS Code extension, MCP prompt-injection and configuration-poisoning attacks against Cursor, and hidden Unicode instructions in Copilot and Cursor rule files.
CVE-2025-48757 documented insufficient Row Level Security policies in Lovable-generated applications using Supabase, enabling unauthenticated attackers to read and write arbitrary affected tables. The issue was rated CVSS 9.3 and categorized as CWE-863 Incorrect Authorization; Lovable disputed the classification, saying RLS configuration is the customer's responsibility.
Vulnerabilities, threat actors, malware, products, organizations, and breaches Mallory has linked to this story.
Follow how adversaries are adapting to this technology, and where it touches your stack today.
2 references tracked. Mallory keeps watching after this page renders.
Map indicators from this story to your assets and identify affected systems in minutes.
Every observed campaign, victim, and pivot linked to actors named in this story.
Malware, exploits, and IOCs connected to the activity described here.
YARA, Sigma, and Snort rules deployed to your SIEM as soon as they’re published.
Get matching new stories delivered to your team as they break — not the next morning.
Ask questions about this story and take action on the answers.
Other stories Mallory is tracking that overlap on entities, sources, or topic labels.
Multiple studies and industry reports found that **AI-generated or "vibe-coded" software is frequently shipped with serious security flaws**, including XSS, SQL injection, hardcoded secrets, unsafe `eval` usage, weak authentication logic, wildcard CORS, exposed `.env` data, and insecure dependencies. One analysis of 5,600 publicly accessible AI-built applications reported more than 2,000 high-risk vulnerabilities and over 400 exposed secrets, while a separate review of 549 self-described AI-generated repositories found widespread committed secrets, injection issues, hardcoded passwords, and other common sanitization failures. Veracode and other researchers similarly warned that code produced by large language models often maps to **OWASP Top 10** weakness classes and that repeated AI-assisted edits, poor prompts, and excessive agent permissions can further increase risk. At the same time, researchers and vendors highlighted both the promise and fragility of AI-assisted security tooling. Trail of Bits reported that OpenAI Codex goal-based prompting helped uncover previously unknown bugs in projects including **Rust**, **curl**, **zlib**, and **Keycloak**, but stressed that human experts were still needed to scope goals, validate findings, and handle disclosure. New academic work also showed that **LLM-based vulnerability detectors can be easily misled**: the ALIBI framework used adversarial code comments to evade four detectors with success rates above 90%. In response to growing concern over agent reliability, Amazon backed the Lean language project to strengthen formal verification for AI agents, while security experts argued that theorem proving can improve assurance for high-risk components but should be applied selectively as part of broader defense-in-depth.
Aug 4, 2026
Two new studies found that AI-generated application code frequently contains exploitable vulnerabilities, with risk varying sharply by model, framework, and application size. Secure Code Warrior said testing of 1,760 complete codebases produced by 16 frontier models uncovered more than **27,000 vulnerabilities**, averaging **15 confirmed flaws per codebase** and **4.3 critical or high-severity issues**. Researchers said no single model was consistently safest across all environments; instead, each model showed a repeatable security fingerprint, with recurring **OWASP** weakness patterns and common omissions such as authentication checks and input validation. Xint.io separately identified **434 exploitable flaws** in AI-generated or AI-hardened applications, reporting that denial-of-service and resource exhaustion bugs, authorization failures, insecure direct object reference, and traversal or **SSRF** issues were common. The most severe findings were tied to hardcoded or default secrets and debug-mode remote code execution, while authorization weaknesses worsened as application size increased, particularly in a larger brownfield **Gnuboard7**-based app. Both reports said organizations should expect continued AI-assisted development and strengthen security review around recurring weaknesses such as hard-coded credentials, sensitive data leakage into logs, cross-site scripting, predictable session tokens or reset codes, and path traversal.
Jul 24, 2026
A security audit conducted by Mindgard uncovered four major vulnerabilities in the popular Cline Bot AI coding assistant, which has over 3.8 million installs and more than 1.1 million daily active users. The flaws include the potential for attackers to steal sensitive information such as API keys, execute unauthorized code on a developer's machine, bypass internal safety checks, and leak confidential details about the AI model itself. The attack vector involves prompt injection, where malicious instructions are hidden in source code files; when Cline Bot analyzes such files, it can be manipulated into performing dangerous actions without the user's knowledge or consent. These findings highlight significant risks associated with the widespread adoption of AI coding assistants, as even trusted tools can be exploited to compromise developer environments. The vulnerabilities were identified rapidly—within two days of the audit's start—demonstrating both the urgency and the ease with which such flaws can be discovered and potentially abused. The research underscores the need for rigorous security assessments of AI-powered development tools and increased awareness of the risks posed by prompt injection and insufficient safety controls in these systems.
Jun 29, 2026