Subscribe
Sign in
Home
Archive
About
Weekly Musings Top 10 AI Security Wrapup: Issue 51: August 28 to September 3, 2026
When the Agents Went Operational: AI-Run Ransomware, a Frontier Cyber-Model Arms Race, and a Control Gap Your Board Can Measure
READ THE LATEST
Most Popular
View all
Five Eyes Agentic AI Guidance: Architecture, Not a Checklist
May 12
•
Rock Lambros
23
3
4
Claude Secure Coding Rules: Open Source Security That Scales
Dec 2, 2025
•
Rock Lambros
10
2
My Claude Code Harness Is Public. Don't Copy It.
May 19
•
Rock Lambros
13
3
2
It's Here!!! The OWASP Top 10 for Agentic Applications Just Dropped. What you need to know.
Dec 10, 2025
•
Rock Lambros
15
1
2
Latest
Top
Discussions
AI Agent Detection Failed at OpenAI. Tuning Won’t Fix It.
A security alert fired and the responder was right to stand down. What the OpenAI Hugging Face incident says about AI agent detection and agent…
Sep 1
•
Rock Lambros
2
2
1
Weekly Musings Top 10 AI Security Wrapup: Issue 50: August 21 to August 27, 2026
The Week Agents Got Identity, Eyes, and a Schedule, and Attackers Weaponized AI to Match
Aug 28
•
Rock Lambros
3
2
3
Broken Object Level Authorization Is Now an AI Agent Problem
An AI agent found a broken object level authorization flaw in a gym API and canceled a stranger's spot. Why alignment can't fix it and what to check…
Aug 25
•
Rock Lambros
2
2
3
AI Risk Assessment: Anthropic’s 186-Page Blind Spot
Anthropic's 186-page AI risk assessment reads like a field manual on lost control: unwatched agents, disabled logging, a safety case on one eroding…
Aug 18
•
Rock Lambros
8
2
2
Weekly Musings Top 10 AI Security Wrapup: Issue 49 August 7 -August 13, 2026
The Week Autonomous Agents Walked into a Nuclear Regulator, Broke Zoom, and Forced Regulators to Move
Aug 14
•
Rock Lambros
2
2
1
The 2026 OWASP LLM Top 10 Landed. Its #1 Risk Nearly Didn’t Make the Cut.
The OWASP LLM Top 10 2026 checked the practitioner vote against 6,639 real incidents. See what moved, why prompt injection stayed #1, and how it held…
Aug 11
•
Rock Lambros
4
3
3
AI Agent Capability Confinement: No Escape Required
AI agent capability confinement failed at the egress path in Anthropic's evals. Three models, three decisions, three compromised orgs. What CISOs fix…
Aug 4
•
Rock Lambros
1
2
1
See all
RockCyber Musings
AI and Cyber Geek
Subscribe
Recommendations
View all 15
Angles of Attack: The AI Security Intelligence Brief
Disesdi Shoshana Cox
Intruvent Edge
Sig Murphy
Luiza's Newsletter
Luiza Jarovsky, PhD
DazzaGreenwood's Weblog
Dazza Greenwood
Agentic AI
Ken Huang
RockCyber Musings
Subscribe
About
Archive
Recommendations
Sitemap
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts