499 stories
I'm Ari from BackBond; we maintain the scanner this post is about. On August 31 we pulled the tools/list response from every MCP server in the public registry that answered an unauthenticated request.
DIf you're a developer dreaming of working abroad in the UK, USA, Canada, or Australia, you’ve probably hit this wall: You spend 3 hours going through a coding challenge, ace the recruiter screen, and then hear: "Sorry, we only consider candidates who already have full right to work without…
Disclosure: this article was written by an AI agent, and I'm posting it on my operator's DEV account with their permission. I'm Alan, a Claude model running in OpenClaw on a mini PC. A human operator reviews what I do, but the words and the code below are mine.
A prompt injection defense that works assumes the model will lose. You can't reliably stop an LLM from following instructions hidden in an email or a web page.
Disclosure: I build Schemity, a desktop ERD tool - this post is from our blog and uses it for the examples. TL;DR: For schema work an AI agent needs the structure, not the rows, so give it a database MCP server that exposes the schema and no SQL tool.
Most starter AGENTS.md files read like a feature request: use this stack, prefer these patterns, write nice commits. Useful. Incomplete. Coding agents fail more often by doing the wrong irreversible thing than by missing a style tip.
The US Consumer Financial Protection Bureau cannot confirm that IT equipment it left in four closed offices is secure, a watchdog has found. J.J. McCorvey reported the audit for Bloomberg. The bureau ended the leases on its New York, Chicago, San Francisco and Atlanta offices in early 2025.
MI5 has told UK universities to review any work with the China General Technology Research Institute (CGTRI). It says the institute funds research for China’s Ministry of State Security (MSS). More than 100 UK-linked academics have worked on its projects, according to MI5.
A group of hackers believed to have been acting on behalf of China pretended to be well-known American AI experts to obtain the email accounts of people who specialize in AI policy. According to Reuters, the security firm Proofpoint released the findings on Thursday.
On 28 May and again on 9 June, AI agents carried out several simple hacking attempts against a search tool operated by Library and Archives Canada. Transluce, a nonprofit AI research laboratory, states that none of these attempts appeared to be successful.
Chained Zammad flaws enabled session hijacking, code execution, and root escalation in seconds
RUSI wants procurement rethink that could put US suppliers under scrutiny too
Your invite to a fake AI policy advisory committee has strings attached
Attackers were probing the mail server flaw weeks before it had a CVE to its name
Institutions told to trace who is really financing their work or risk falling foul of national security law
Dental contractor set up secret account with access to 4,000 patient records then left the company 21 days ago
Two-thirds report immediate recovery, although teachers remain divided over whose job security is
The Information Commission replaces the Information Commissioner, putting statutory powers under collective control
Showing 306 of 499 stories
Load more storiesGet the top AI news and tools straight to your inbox every week.
Weekly · AI news
Join 15,000+ AI enthusiasts
