OWASP GenAI Security Project · December 10, 2025

OWASP Top 10 for Agentic Applications for 2026

Why it matters

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.

My takeaway: Map each agent, tool, memory store, identity, and inter-agent channel to the relevant risks, then collect evidence for least privilege, schema validation, provenance, monitoring, and kill switches. Convert the taxonomy into abuse cases and tabletop scenarios, and verify controls with red-team tests tied to real business impact.
Keep exploring

More curated notes connected through AI Red Teaming and Prompt Injection.

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.

Google Cloud Security Blog · tool

Now in preview: Find and fix software vulnerabilities with CodeMender

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.

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.