After months of real-world testing of AI copilots, chat interfaces, and AI-generated apps, Terra Security releases a new module for continuous AI Penetration Testing to match AI development velocity and use cases

BOSTON: Terra Security, a pioneer in agentic Continuous Threat Exposure Management (CTEM), today disclosed findings from recent continuous penetration testing engagements revealing exploitable vulnerabilities in AI-powered applications, copilots, and AI-generated code workflows. In response, the company has released a new module as part of its continuous penetration testing platform that allows security researchers to continuously simulate attacks on AI systems at scale to discover such vulnerabilities.

Terra has conducted adversarial testing across applications built with AI coding tools such as Claude Code, rapid AI app-generation platforms such as Loveable and Base44, and enterprise software that embeds AI chat interfaces and copilots over the past several months. The company reports finding recurring vulnerability patterns that differ from traditional software security flaws, such as CVE-2026-25724, discovered in Anthropic’s Claude Code by Terra Security researchers.

The research has identified that in 100% of applications that embed AI chats or copilots, AI-related security vulnerabilities were discovered.

Real-World AI Vulnerabilities Observed in Large Enterprises' Production Environments:

• Prompt injection attacks against AI copilots
• Indirect prompt injection through embedded or third-party content
• Sensitive system prompt leakage
• Cross-tenant data exposure in AI copilots
• Privilege escalation via AI tool execution chains
• Reverse shell execution through AI-enabled command workflows
• Broken authorization logic in AI-generated business processes
• Exposure of internal APIs introduced during AI-assisted feature expansion
• Cross-site scripting via LLM Prompt Injection with authentication bypass

“Some of these issues did not stem from malicious intent or overt misconfiguration, but from complex interactions between AI agents, application logic, and operational tooling,” said Shahar Peled, CEO and Co-founder of Terra Security. “With AI systems committing code with vulnerabilities, modifying configurations, and interacting with pipelines, organizations need visibility into real-world exploitability in production environments, not just theoretical risk. We are proud to be able to provide the means for pentesters to monitor these actions continuously using the Terra platform.”

As AI agents are granted broader access to repositories, APIs, and infrastructure tools, small validation gaps can quickly scale across environments. Anthropic’s recent security enhancements to Claude Code reflect the industry’s growing focus on discovering vulnerabilities at the code level. Terra Security supports these advancements, but emphasizes that code-level vulnerabilities alone do not determine exploitability in deployed live applications.

“Traditional scanners look for known patterns,” said Gal Malachi, CTO and Co-Founder of Terra Security. “What we’re seeing with AI-powered systems is contextual vulnerabilities in cases where the model behaves as designed, but the surrounding application or permission model allows unintended outcomes. A prompt injection may not resemble a conventional code flaw, yet it can still expose sensitive data or trigger unsafe actions if safeguards are incomplete.”

About Terra Security

Terra Security provides Agentic AI-Powered continuous penetration testing aligned to code changes and evolving attack surfaces, combining a swarm of trained AI Agents with human supervision for safety and control. The company works with Fortune 500 organizations to ensure every attack surface is covered across the web, AI, internal apps, APIs, mobile, networks, and the cloud. Winner of the 2025 CrowdStrike/AWS/NVIDIA Cybersecurity Accelerator, and backed by SYN Ventures, Felicis, Lama Partners, SVCI, Underscore VC, Dell Technologies Capital, and Capital One Ventures. The company is based in the U.S. and Tel Aviv. Visit terra.security to learn more.

Fonte: Business Wire