AI
jqwik Logs Now Speak to AI Agents, Turning Test Output Into a Supply Chain Surface
jqwik 1.10.0 adds an AI-agent-facing test log message, raising new questions about stdout, prompt injection, and coding agent trust boundaries.
AI
Anthropic published Claude containment details, and 24 AWS key thefts explain the risk
Anthropic detailed the isolation design behind Claude Code and Claude Cowork. The numbers turn agent security from approval prompts into sandbox, VM, and egress policy.
AI
Copilot Memory now has an off switch, and agent memory becomes a permissions problem
GitHub added deletion guidance, repository-level off switches, CLI controls, and scope prompts to Copilot Memory. The update turns coding-agent memory into a governance surface.
AI
Decepticon 1.1.3 Tests the Guardrails for Autonomous Red-Team Agents
Decepticon 1.1.3 shows that red-team agents are now competing on rules of engagement, sandboxing, graphs, release integrity, and auditability.
AI
Codex now works on a locked Mac, and Goal mode redraws the agent boundary
OpenAI added Appshots, Goal mode GA, browser annotations, locked computer use, and admin analytics to Codex. The update shows coding agents becoming longer-running workers.
AI
OpenAI Adds Live Vote Counts to Election Answers
OpenAI outlined its 2026 election safeguards, combining AP vote counts, voting information, Codex Security, SynthID, usage policy, and political bias evaluations.
AI
620,000 attacks expose a 35-point safety gap in reasoning models
TELUS Digital tested 34 AI models with more than 620,000 adversarial attacks. The benchmark shows why enterprise AI safety is now an operating discipline.
AI
CLAUDE.md Became an Attack Surface, TrapDoor's Invisible Instructions
TrapDoor combines malicious npm, PyPI, and Crates.io packages with poisoned AI coding instruction files.
AI
Claude Containment Shows Agent Security Is Now Blast Radius Design
Anthropic’s Claude containment write-up shows agent security moving from prompt defenses toward environment isolation, scoped tokens, and blast-radius control.
AI
After 10,000 Bugs, Mythos Moves the Bottleneck to Patching
Anthropic Project Glasswing suggests AI security models may shift the bottleneck from vulnerability discovery to verification, disclosure, and patch throughput.
AI
Claude shows why agent security moved beyond approval prompts
Anthropic’s Claude containment writeup shows agent security shifting from prompt defenses and approval dialogs toward runtime isolation and blast-radius control.
AI
The 3-second approval device trying to hold agent authority
Foundation Passport Prime is an experiment in moving final approval for AI agents out of the browser and into dedicated hardware.