7 articles.
A concrete look at Anthropic's October 2026 'mods' addition: what it lets a team actually block, and why agent permissions matter more than raw model capability.
Empirical studies show a meaningful share of AI-suggested code contains security flaws. The risk is highest when students and beginners accept suggestions without review.
Studies across multiple languages and scenarios show GitHub Copilot can produce insecure code suggestions at nontrivial rates. The risk is highest when developers accept suggestions uncritically without security review.
The OWASP Top 10 for LLM applications lists the most common security risks when deploying AI features. Here is what each means in business terms and which to prioritise first.
Employees pasting sensitive material into unsanctioned AI tools creates data-exposure and compliance risk that most organisations have not governed. The core problem is unapproved tools plus confidential input, not the model itself.
USENIX Security 2025's Distinguished Paper ran 16 models across 576,000 code samples and counted 2.23 million recommended packages, of which 440,445 were hallucinated and 205,474 were distinct names that exist nowhere in PyPI or npm. Closed models hallucinated at 5.2% against 21.7% for open models. When researchers repeated 500 prompts ten times each, 43% of the hallucinated names reappeared in every single run, which is what makes the attack possible.
Coding agents multiplied the code security teams have to review, and the vendors selling AI review tools all report spectacular accuracy. Here is what one vendor's own benchmark against frontier models shows, and why the agent attack surface is the part worth acting on.