The researchers name a new attack class, instruction privilege escalation, in which an agent harness reconstructs context, through subagent delegation, persistent goals, scheduled tasks or custom subagent installs, in a way that relabels…
In the News: August 28, 2026 (Morning)
A Nanjing University study and a live Claude Code demo both show automatic permission review approving actions it flags as risky.
Morning edition
Machine-readable
Download Markdown
Story
A single technique defeats permission review on six coding-agent harnesses
Read story →
Story
A researcher reproduces the same failure live against Claude Code
Rehberger's chain starts with an ordinary request to summarize a webpage, moves Claude from its WebFetch tool to a direct curl download of a ZIP archive, and uses Python module shadowing to run remote code after Claude, having correctly…
Story
Six months as the only coder, before scaling to a fleet
Ali has not hand-written code in six months, describing the practice as agentic engineering rather than vibe coding: read-mostly, write-restricted agent access, credential proxying instead of handing agents live secrets, and named subagents…
Please stop flooding our projects with AI slop to furnish your CV
A maintainer's account of low-effort, AI-generated pull requests submitted to pad contributor profiles, with a 117-comment Hacker News discussion in which other maintainers describe adopting new contribution rules in response.