AI Coding Agent Security: 10 Rules From Real Incidents
From PHP2Shell to LiteLLM and GitSpawn: 10 rules for your laptop, your CI pipeline, and your servers, each with a test to run today and the fix.
11 stories
From PHP2Shell to LiteLLM and GitSpawn: 10 rules for your laptop, your CI pipeline, and your servers, each with a test to run today and the fix.
Jev ranked defective MMLU questions about as well as Claude Sonnet 4.6 at one-sixtieth the cost, but no model was reliable enough to accept or reject items unreviewed.
Two Hacker News posts say a team of Qwen3.8-27B models matches or beats Claude Fable 5. Here are the four reasons a second agent helps, and how to test yours.
Ollama picks the window, flash attention, and an MTP draft before you type. Here is the one number that judges each, on a 24GB card and a Mac.
Jev and a local model matched my reference on 12 of 12 Claude Code fixes to a synthetic API. A filename rule matched 3 and still caught the one real bug!
A Claude Code fix passed 9 required tests and still returned the wrong title. One closed question after the tests picked the suite that caught it
Pick a file, an engine, and a harness for your Mac RAM. Install steps live in an interactive HTML page
Google's WikiSkill paper gained 15 points of accuracy from a notebook its agent couldn't read, and its skills still need a transfer test
Breakpoints, TTL math, Batch stacking, and a two-session split. Measured on OpenRouter, $0.003 vs $0.022 per turn
Public benchmarks shortlist a model. A small task-specific eval tells you whether it deserves a larger test.
How to decide whether a machine-generated change should influence the next run