Agentic Ai

A security-leadership field guide to the AI-agent benchmarks vendors quote: WorkBench, JobBench, BigLaw Bench (+ BigLaw Bench: Research), SWE-bench / SWE-bench Verified, GAIA, τ-bench / τ²-bench, WebArena, MLE-bench, BrowseComp and AssistantBench. What each one measures, how grading differs (programmatic vs rubric vs human), why a high score on one says almost nothing about another, and the questions to ask when a benchmark number lands on your desk. Tied to Google’s Harness² work, which is a reminder that a score is the model plus its harness — not the model alone.

A security-leadership comparison of the main ways to make an AI agent better without retraining the model: Google’s Harness² (recursive harnessing of the whole scaffold), GEPA (reflective prompt evolution), DSPy (a pipeline compiler with optimisers), ADAS (a meta-agent that writes new agents in code), Reflexion (runtime verbal self-reflection) and plain ReAct as the baseline. What each optimises — prompts, few-shot demos, tools, topology, control flow or memory — the data and cost each needs, its maturity, and the governance implications (self-modifying agents, code generation, egress, auditability). Includes an honest note on "PRISM," a name that maps to several unrelated methods.

Google’s Harness² lets an AI agent rewrite its own harness — prompts, guardrails, memory, tools — per task, weights fixed. A calm read of what it is and the governance controls it demands.

How secure is Google AX vs LangGraph, CrewAI, Microsoft and OpenAI's agent orchestrators? Compared on sandboxing, egress, spend limits and audit trails.

A local zero-day in Meta’s Muse Mac client lets unprivileged malware hijack prompts, steal the agent’s auth, and pivot to a linked iPhone.

Hacktron chained a libheif overflow, RCE on community.openai.com, and an SSO flaw into ChatGPT/Codex takeover and internal repo access in under 72 hours.

VirusTotal released VTAI: a free, no-API-key MCP server and REST API letting AI coding agents check file, URL, domain and IP reputation. What the 7 tools actually do, the real limits, and what to know before wiring it into an agent.

VirusTotal’s free VTAI lets any AI agent check file and URL reputation in one call. Before your engineering team wires it in, here is the governance checklist: what it can leak, what it won’t block by default, and how to roll it out safely.

VirusTotal shipped VTAI, a free MCP server and REST API for checking files, URLs, domains and IPs — no paid key required. Here is how it actually compares to the abuse.ch feeds, urlscan.io, Google Safe Browsing and MetaDefender Cloud on coverage, quotas and auth friction.

A reference architecture for the three unsolved problems of deploying AI agents at scale: identity (zero standing privilege), security (runtime guardrails plus a quarantine path), and observability (trace-first debugging). Nine components, explained — plus an interactive tool to self-score your own environment.

PentAGI is a 24k-star open-source AI agent that plans and runs pentests with Nmap, SQLMap and Metasploit. What it does and what to check before you run it.

Prompt injection explained for practitioners: direct vs. indirect attacks, why tool-calling agents make it worse, real attack patterns, and the defenses — treat tool output as data, scan it, and constrain what agents can do.

Ultrafuzz, an agentic smart-contract fuzzing orchestrator, is now open source. Its four experiments reveal what actually makes AI-assisted vulnerability discovery work — and the lessons apply well beyond DeFi.

A deep dive into the Domain-to-Domain (D2D) agentic protocol — the coordinator, worker, and killer node model that lets autonomous AI agents collaborate across security domains without human-in-the-loop bottlenecks.

What do the actual files look like inside a production D2D worker node? We break down the manifest, system prompt, and tool definitions that make each agent composable, safe, and auditable.

The coordinator node is the brain of a D2D agentic system. Here's how it decomposes missions, handles partial failures, and knows when to escalate rather than guess.

Lessons from wiring up a D2D multi-agent system to a production SOC: the PagerDuty integration, the human review queue, what broke, and what surprised us.