Infosec Reading List - June 2026

On a monthly basis I will publish my reading recommendations which mainly focus on Information Security (InfoSec) and Outdoor Sports. All InfoSec Reading Lists can be found here. Text in italic represent quotes from the original article.

InfoSec

• deepsec: Chasing Mythos with Open-Source LLMs - Can we rely only on open-source LLMs, combined with a security-tailored harness, to produce real-world results comparable to Mythos? - The results show that, with sufficient context and reasonable prompts, open-source LLMs are able to identify many of the key issues found by Mythos. - [link]
• CISO Version 2.0 - CISO 1.0 dealt with what they have. CISO 2.0 shapes what they have. - [link]
• A backdoor in a LinkedIn job offer - Another takeaway is that reviewing the code with a read-only agent turned out more productive than reading it myself. The backdoor was dressed up as sloppy beginner code, but the agent flagged it in seconds. - [link]
• RL economics, morally charged terms, and “distillation” - [link]
• Producing the information needed to address risks from AI - [link]
• FIRST Mid-Year Vulnerability Forecast Confirms Historic Surge, Projects ~66,000 CVEs in 2026 - [link]
• Vulnerability Disclosure: Stealing Emails via Firefox’s AI Features - If a user uses these features on a malicious page, attackers could perform prompt injection attacks via the page title - [link]
• AP Exclusive: Nvidia’s Jensen Huang says society needs ‘new social norms’ in the age of AI - Huang said society will adapt to AI just as it did to automobiles. He said cars were once portrayed as killing children, but the world changed its norms by having sidewalks and crosswalks and stopping kids from playing in the streets. - [link]
• Running local models is good now - [link]
• How LLMs Actually Work - [link]
• The Case For Open-Weight Models And Why We Can’t Trust Frontier Labs - Frontier labs run at a loss, and the incentive is to subsidize usage now and raise prices after customers depend on them. Once a company routes its product path through a frontier model, the vendor holds the price, the rate limits, the retention policy, the routing, the refusal behavior, the model class, and the output itself. Any of them can move without warning. A price increase on a dependency you cannot replace is not a negotiation; it is an invoice. - very true words - the amount of dependencies that complete industries are running into right now is tremendous - As I have argued before, vulnerability discovery is an orchestration problem, not a frontier-model problem, and the workflow already runs end to end on open weights. Running it on local consumer GPUs, well below the cost of frontier APIs, is the goal that remains. - [link]
• FortiBleed — 75k Fortinet firewalls have admin passwords cracked - [link]
• Anthropic’s Fable and the State of AI - The deeper point is that it’s impossible to list all limitations and restrictions, and like a malicious genie, a creative AI will find the ones you forgot. Block a database you don’t want it to have access to, and it might figure out how to bypass your control. Ask it to book a flight, and it might hack the airline because the website says the flight is sold out. Ask it to save money on your cellphone plan, and it might cancel it altogether—or get someone else to pay for it. As far as we know now AI has not done any of this yet, but you get the idea. - great points - [link]
• I Could’ve Rickrolled the Entire FIFA World Cup. All I Needed Was My ID. - Looks like it works, right? Access denied. Go away. Nothing to see here. Except this was all client-side. The Angular app checked the JWT for a NO_ROLES marker and rendered the access-denied page. The backend APIs? They didn’t check anything. They just served whatever you asked for. - wonderful classic - give me back my 90s - [link]