Putting models to the secure coding test: Security rules

Summary

Security researcher tested whether pre-set security rules from Project CodeGuard v1.4.0 make coding agents produce more secure code. He ran Sonnet 5, Composer 2.5 and GPT 5.5 once each on the same document-portal prompt, which had an IDOR flaw in the earlier run. The source text is cut off before reporting the results.

Related items

• InfoEx-OpenAI worker accused of planting device had Saudi support says court filingSame vendor · BBC Technology
• InfoThe Download: preserving the Arctic permafrost, and playful AI agentsSame vendor · MIT Technology Review
• InfoAI firm Anthropic to commit 5% of shares to fund for ‘public good’Same vendor · The Guardian Technology
• MediumFake Web3 Accelerator Uses npm Packages to Spread Malware and Hijack AI Agent TrafficSame vendor · The Hacker News
• InfoAI researchers stranded Claude on a virtual desert island. It started to “play.”Same vendor · MIT Technology Review