Four vendors shipped narrower permissions at the exact moment an agent acts, and a Rust crate that ran malware during cargo build showed why the moment of execution is the only place the control matters.

Four vendors shipped narrower permissions at the exact moment an agent acts, and a Rust crate that ran malware during cargo build showed why the moment of execution is the only place the control matters.

The agent skill turned into a package format this year, and the packaging shipped well ahead of the registry, the signature, and the scanner that a package format normally needs.

Every launch in the last 48 hours assumes nobody will actually read the agent's work, and ships a substitute for reading it.

Every significant capability gain published in the last 48 hours came from changing the harness around the model instead of the model itself, and none of it shipped with a security evaluation.

Three labs spent this week engineering containment against their own models, and the thing being contained is offensive security capability that arrived faster than any of them planned for.

Five gates went up around the AI stack in forty-eight hours, and the GitHub daily board is quietly voting for everything you can pick up and carry out.

AI now reviews code and attacks it, and only the attacking side gets to iterate against live feedback.

Three separate moves in 48 hours all changed the layer between your app and the model, and not one of them was a model.

The arrayref attacker yanked every clean release 24 seconds after publishing the poisoned one, which made Cargo's own deprecation warning…

AI-Infra-Guard's skills and MCP scan is the most useful free thing you can point at an agent stack, but the platform running it holds your…

Ray protected an unauthenticated job-submission endpoint with a string check on the User-Agent header, and DNS rebinding turned any open…

OpenBot's reusable idea is the ordering rather than the sandbox: the audit row is written before the action so a crashed or refused call…

The reusable idea in Anthropic-Cybersecurity-Skills is the per-skill framework mapping rather than the skill count, and the repo's own…

Teams with coding agents went from 21 to 65 pull requests a week while the number of humans reading them stayed flat, so review has already…

StateM's reproducible claim is the roughly $15 price rather than the 95.3% score, because Terminal-Bench's published leaderboard subtracts…

Bankruptcy court has become a training-data supply line, and the privacy machinery in the code protects the customers a dead company had,…