AI agents
9 posts
20 min read
PHP2Shell: why a WAF alone won't stop this PHP RCE
PHP2Shell (CVE-2026-109618, CVE-2026-109619) is fixed in PHP 8.2.35, 8.3.36, 8.4.27 and 8.5.12. Why a proxy alone fails, and how AI agents widen the gap.
- Vulnerability management
- LLM security
- AI agents
21 min read
OpenAI Medicare hack: what it means for Australia's AI guardrails
An OpenAI agent got into a Medicare portal and Australia found out three months later. The verified timeline, legal gaps, coming guardrails, and what to do.
- AI governance
- AI agents
- Regulation
25 min read
Grok 4.7 vs GPT-6 Astra vs Claude: a CISO's security comparison
Grok 4.7, GPT-6 Astra and Claude Opus 5.5 compared on capability, safety evidence, enterprise controls, Australian data residency and platform integrations.
- AI governance
- LLM security
- AI agents
29 min read
The agentic SOC is real, and your logs are now prompts: how AI security monitoring actually works, and where it breaks
Microsoft, Google and CrowdStrike now ship autonomous agents that triage alerts in real time with no analyst in the loop. What agentic SOC tooling actually does, the research showing attackers can prompt-inject it through ordinary log fields, and the control set that holds under APRA scrutiny.
- AI agents
- Detection engineering
- SOC
19 min read
AI supply chain security: four ways code now enters your estate without a vendor review
Model weights, agent skills, MCP servers and packages your coding assistant invented all execute in your environment, and none of them trigger a vendor assessment. The documented incidents, the measured scale, and the controls that close the gap before CPS 230 makes it an audit finding.
- Supply chain
- Third-party risk
- AI agents
15 min read
Jailbroken AI as an attack tool: how attackers actually use it, and how to defend
Attackers jailbreak frontier models, rent dark LLMs like WormGPT, and bolt AI onto phishing, deepfake fraud, and agentic intrusions. The documented tradecraft, the real incidents, and the defence-in-depth controls that hold, with Rust guardrail code.
- AI agents
- Jailbreaking
- Prompt injection
24 min read
OpenClaw, WhatsApp and Telegram: the phone-linked AI agent threat model, the attacks already in the wild, and the gold-standard alternatives
OpenClaw lets anyone wire a personal WhatsApp or Telegram account to an AI agent in ten minutes. Bitsight found 30,000 instances exposed on the public internet in a fortnight. This is the architecture, the attacks, the config that breaks it, and the official-API pattern that holds.
- AI agents
- OpenClaw
21 min read
Long-term memory for agnostic agents: a working architecture on Bedrock AgentCore
Bedrock AgentCore gives you a managed runtime, a long-term memory store, and a deliberately framework- and model-agnostic SDK. That keeps the agent code portable while the memory plane becomes the new audit liability. Here is the architecture that uses AgentCore Memory properly, the governance controls memory-poisoning and Privacy Act obligations force on top of it, and the rollout cadence that keeps the deployment defensible.
- AWS
- Bedrock
- AgentCore
20 min read
OAuth scopes weren't built for AI agents: the delegation model that holds up under prompt injection
OAuth scopes assume a human approves once, an app does narrow work, and the trust horizon is months. AI agents break every part of that assumption. The architecture that holds is a two-principal model with short-lived delegation tokens, ReBAC for structure, ABAC for context, and per-action consent gating destructive operations. Here is the design and the rollout.
- AI agents
- Authorisation
- ReBAC
Get started
Talk to the security lead who would do the work.
A thirty-minute discovery call costs nothing. We confirm fit, scope, and timing, then issue a fixed-fee statement of work within two business days.