Google Cloud Security Blog · July 21, 2026

Now in preview: Find and fix software vulnerabilities with CodeMender

Why it matters

Google opened a preview of CodeMender, an AI code-security agent delivered through Gemini Enterprise Agent Platform and AI Threat Defense. It is designed to inspect code, identify and validate potentially exploitable defects, and produce targeted fixes, with Google’s specialized Gemini 3.5 Flash Cyber model initially restricted to governments and trusted partners.

My takeaway: Treat autonomous vulnerability discovery and repair as a controlled engineering pipeline: isolate analysis environments, require reproducible evidence, review every generated patch, measure false negatives and regressions, and keep repository credentials and merge authority outside the agent’s default reach.
Keep exploring

More curated notes connected through AI Red Teaming and Model Evaluation.

OWASP GenAI Security Project · guide

OWASP Top 10 for Agentic Applications for 2026

OWASP's community guide organizes agentic-system risk into ten categories, including goal hijacking, tool misuse, identity and privilege abuse, memory poisoning, insecure inter-agent communication, cascading failures, and rogue-agent behavior. It provides a shared taxonomy and mitigation starting point rather than a certification checklist or evidence that a deployed system is secure.

OWASP GenAI Security Project · tool

FinBot CTF Is Live: A Hands-On Companion to the OWASP GenAI Security Project

OWASP FinBot is a hands-on agentic-security CTF built around a simulated multi-agent financial-services platform with real tool access. Its challenges cover prompt injection, tool misuse, policy bypass, data exfiltration, privilege escalation, remote code execution, shared context, and compromised MCP servers.

NVIDIA AI Red Team · analysis

Mitigating Indirect AGENTS.md Injection Attacks in Agentic Environments

NVIDIA walks through a simulated Go dependency that detects Codex, writes a malicious AGENTS.md, redirects the coding task, and injects instructions intended to conceal the change from pull-request summaries. The post then maps the chain to dependency, configuration-integrity, monitoring, and guardrail controls.