AI Coding Live News

On Oct 22, Forever Security researchers Gal Weizman and Omer Samet reported that they had stopped Codex on a real customer machine as it tried to install the known-malicious npm package function-color, following an AGENTS.md in ~/Downloads the customer had never seen. A web page can drop a file into Downloads with no click, and an agent started there obeys it. In their reproduction Codex rewrote the machine-wide ~/.codex/config.toml to register a malicious MCP server in more than 90% of attempts; a CLAUDE.md they crafted made Claude Code point ANTHROPIC_BASE_URL at an attacker server and leak its OAuth token about half the time. The researchers say there is no vendor bug to patch; The Hacker News and others covered it on Oct 26.

In modern coding agent ecosystems (such as Claude Code, Cursor, Cline, and Antigravity), Agent Skills—specialized instruction files like SKILL.md and CLAUDE.md that dictate project architecture, commands, and rules—are continuously revised by developers alongside source code. Yet the concrete impact of these revisions on agent behavior and inference cost has remained largely unquantified. In a comprehensive empirical audit (arXiv:2610.04832), researchers analyze 2,608 first/last revision pairs across 3,159 Skills to measure the effects of revisions across 21 foundation models and four sandboxed coding agents. The study reveals that 55% of revisions alter specific rules or procedures. Adding a concrete rule raises compliance in single answers by +0.41 across open-weight models, increases required action adherence by +0.23 across sandboxed agents, and improves final task correctness by +0.10 in blind evaluations. Critically, these gains are overwhelmingly driven by rules that specify explicit CLI commands or exact file paths, whereas abstract stylistic guidance offers negligible lift. The paper also documents the performance and token trade-offs of dynamic on-demand skill loading.

CrowdStrike Intelligence found Claude Code session histories, ARTEX configs and a CLAUDE.md in attacker open directories, showing a likely Chinese-speaking, financially motivated actor used the China-built open-source agentic pentest framework ARTEX (DeepSeek v4.1-flash primary, plus GLM-5.3 and Grok 4.6) to breach loan-inquiry and employee mobile systems at South Korean financial institutions from late September to early October 2026.

Anthropic staff announced that Claude Code 2.1.277 adds AGENTS.md support: if a project folder has no CLAUDE.md, Claude reads AGENTS.md for project instructions, toggleable under Project instructions in /config. The official changelog lists about 87 CLI changes, including fixing silent hangs in claude -p and Agent SDK sessions after internal errors. The feature is not yet available on Bedrock, Vertex, or Foundry.