About AI Sec Weekly

Sourced AI security news and analysis.

What this site covers

AI Sec Weekly is a briefing on AI security: the incidents, vulnerabilities, tooling changes and regulatory moves worth knowing about, each one linked back to its source. It is a synthesis of the public record, written for people who cannot read every advisory themselves.

• Prompt injection and jailbreak research, including the delivery channels behind each new CVE
• CVEs in AI and ML infrastructure — gateways, serving stacks, vector stores, agent frameworks
• Agentic AI failures: tool-call hijacking, excessive agency, and the AI supply chain
• Guardrail, firewall and detection tooling, and what the published benchmarks do and do not show
• Standards and regulation: OWASP LLM Top 10, MITRE ATLAS, NIST AI RMF, and enforcement actions

14 articles are published so far. New ones are announced on the RSS feed.

Where to start

The reference pages are the ones worth bookmarking, and they get revised whenever the underlying research or advisory changes:

• Prompt injection attack examples
• LLM prompt injection defense
• Prompt injection detection tools
• LLM jailbreak defense techniques

If you have skipped a stretch of digests, the catch-up builder assembles one brief from the weeks you missed, filtered to the topics you actually track. It runs entirely in your browser.

How these articles are produced

Articles here are researched from primary sources: vendor and project documentation, published standards and specifications, research papers and preprints, and measurements published by whoever took them. Drafts are produced with AI assistance and then edited against those cited sources before anything is published.

No article on this site is based on first-hand testing in a private lab, and nothing here should be read as a measurement report of its own. Where a number appears, it comes from a source that is named, so you can check the original instead of taking this site's word for it.

Everything is published under a single editorial byline. That byline is a publishing identity for the site, not a claim about a named individual, and it does not carry professional credentials.

Corrections

Corrections are welcome. If something here is wrong, out of date, or attributed to the wrong source, email hello@aisecweekly.com with the page address and what it should say. Substantive corrections are made in the article itself rather than quietly dropped.

How this site is funded

This site currently runs no affiliate links, sponsored posts, display advertising or paid placements. If that changes, the disclosure page will say so.

Contact

Email: hello@aisecweekly.com
Site: aisecweekly.com
Published by: AI Sec Weekly Editorial

See also the privacy policy, the terms of use, and the editorial disclosure.