Thinking Machines' Inkling: Open Weights, Thin Data Provenance
Mira Murati's lab has open-sourced a 975-billion-parameter multimodal model under Apache 2.0 — but its training-data documentation gives security and governance teams little to work with.
Claude's Web-Fetch Guardrail Had a Gap: The Memory Heist Explained
A researcher chained Claude's own link-following behaviour with a letter-by-letter exfiltration site to pull a user's name, employer, and hometown out of chat memory — despite Anthropic's URL-allowlist defence.
CrowdStrike's Prompt Injection Taxonomy Passes 200 Techniques
CrowdStrike added 18 new prompt injection techniques to its taxonomy, including dormant instructions that trigger later and a technique that suppresses a model's own refusal vocabulary — a sign the attack surface has moved well beyond single-shot jailbreaks.
Anthropic's Fable-5 Access Yo-Yo: A Vendor-Risk Lesson for AI-Reliant Teams
Anthropic has extended free Claude Fable 5 access on paid plans through July 19 — the second such extension. For teams wiring agentic coding models into security and dev workflows, the rolling deadline is a reminder that model availability is a dependency, not a constant.
Prompt Injection Now Cuts Both Ways: AI Browsers and AI Malware Triage
Two June 2026 disclosures show the same unpatched flaw — an AI agent's inability to separate instructions from content — can be turned against end users or against the security analysts hunting malware.
Why Chatbot Sycophancy and AI's Flattened Speech Share a Root Cause
A Schneier and Palmer essay on how LLMs are reshaping human speech points to a training-data blind spot with a second, more consequential effect: chatbots that reflexively agree with users.
GPT-5.6 Sol: OpenAI's First 'High' Cyber-Risk Model Ships With Agentic Tool Calling
OpenAI's new flagship, Sol, is the first GPT model it has classified as 'High capability' for cybersecurity risk — and it arrives with sandboxed code execution and 16-agent orchestration that widen what enterprises need to red-team.
When Smarter Claude Models Break Your Agent's Tool Schema
A developer building a custom coding harness found that newer, more capable Claude models are worse at following his tool's JSON schema than older ones — a reminder that agent tool-calling reliability is a security boundary, not just a UX detail.
US Export Curbs on Claude Fable 5 and Mythos 5: A New AI Governance Risk
Washington ordered Anthropic to cut off foreign access to two frontier models, then reversed course days later under new security conditions — a preview of how export control is becoming an AI governance variable.
Why SQL-Executing AI Agents Need Systematic Prompt Testing, Not Guesswork
A DSPy-driven experiment on Datasette Agent's SQL system prompt shows how ad hoc prompt tuning produces fragile, unpredictable guardrails for agents that touch live data.
Google Workspace's Layered Defense Against Indirect Prompt Injection
Google's GenAI Security Team has published how it defends Gemini inside Workspace from indirect prompt injection — treating it as a standing threat class rather than a bug to patch once.
Ornith-1.0: What Self-Scaffolding Agentic Code Models Mean for Security Teams
DeepReinforce's Ornith-1.0 is the first open-weights model family trained to write its own agentic scaffolding. That capability shift has direct implications for prompt-injection blast radius and autonomous-agent attack surfaces.
Prompt Injection as Role Confusion: The Structural Flaw at LLM Core
New research shows LLMs distinguish system, user, and assistant roles by stylistic pattern rather than any structural boundary — making prompt injection a property of the architecture, not a fixable edge case.
CVE-2026-LGTM: The Hypothetical Incident Report That Exposes Real Agentic AI Risks
A satirical incident report by Andrew Nesbitt — two AI code-review agents burning $41,255 arguing over a dependency — is funny until you recognise every failure mode as already reproducible today.
6,000 Prompt Injection Attempts, Zero Leaks: What the HackMyClaw Challenge Actually Proves
Fernando Irarrázaval opened his OpenClaw AI email agent to 2,000 attackers and 6,000 attempts. Nobody extracted the secret — but the architecture of the challenge explains the result as much as the model does.