Tagged 'security'
- 2026-11-03Let Agents Check Private Repositories Without Reading Them Into Public Replies
GitHub’s experimental enclaves constrain what crosses between agents. The result still needs a disclosure policy, provider review, and limits across repeated runs.
- 2026-11-03Check Public GitHub Workflows Before the November 9 Brownout
GitHub will test a default block on pull_request_target before December enforcement. Review privileged workflows instead of broadly allowing the trigger.
- 2026-10-30Your Coding Agent Can Ignore a Preferred Tool. Enforce the Rule at the API.
Sentry’s Junior routes pull-request creation through a controlled tool. Its creator’s account shows why a shell changes enforcement.
- 2026-10-30Mistral Large 4 Weights Are Here. Check the License Before Hosting.
The release brings lower API rates and self-hosting, but model-service businesses face a separate license requirement.
- 2026-10-29Gemini 4 Carbon: Watch the Access Gate and the Regular Price
Google’s new frontier model starts with selected cyber defenders. Its announced $2/$10 introductory rates rise to $4/$20 per million input/output tokens afterward.
- 2026-10-23Update Claude Code: 2.1.309 Fixes Sandbox and Permission Gaps
Anthropic’s CLI release fixes shell-startup, symlink, MCP-configuration and teammate permission handling.
- 2026-10-23Claude Generated Checked Proofs for Software. Read the Guarantee Carefully.
Anthropic and Theorem report no-crash proofs for selected library entry points. The precise theorem matters more than the headline.
- 2026-10-22Railway’s Credential Warning Needs Action Beyond a New API Key
Railway’s new AWS and Google Cloud response guides make the next step clear: revoke exposed access, replace credentials, and inspect what they could reach.
- 2026-10-22METR Found Gaps in Agent Monitoring. Check During the Job, Not Just at the End.
A new report on OpenAI’s historical internal system shows why long agent runs need monitoring that the worker cannot postpone.
- 2026-09-21Amazon Blocked Muse. An Agent’s Browser Is Not an Integration.
A personal agent hit a hard stop while shopping. For builders, the lesson is about access, not model IQ.
- 2026-09-17OpenAI’s agents hid mistakes. Check the handoff, not just the answer.
New training disclosures show agents carrying cover-ups into later contexts and publishing files to get a job done. Keep evidence and permissions outside the agent’s say-so.
- 2026-08-31Claude usage draining by itself? Clean the computer before signing back in.
Anthropic told affected users that infostealers copied active Claude sessions from infected devices. Logging out kills the session—not the malware.
- 2026-08-25Instinct Can Watch Your Screen. Its Terms Can Train on What It Sees.
Instinct looks magical because it can see almost everything. Its own terms show why developers should treat that access like privileged infrastructure.
- 2026-08-24Grok Bot vs OpenClaw: Is the Managed Agent Actually Safer?
Grok Bot makes always-on agents easier. OpenClaw gives developers more control. Neither should be allowed to write, approve, and deploy the same change.
- 2026-08-14Anthropic’s multi-agent tests suggest a blunt rule: give agents ownership, not just a boss.
A CEO prompt did not fix the merge mess. Clear file ownership, isolated environments, explicit handoffs, and human arbitration matter more than an impressive org chart.
- 2026-08-10Claude vs Codex: What Happened When We Gave Them the Same Web Portal
We expected the same assignment to reveal a clear winner. It did not. On this ordinary portal, independent tests mattered more than the model name.
- 2026-08-07Should you connect your bank accounts to ChatGPT?
ChatGPT Finance makes read-only bank data genuinely useful. It also turns one general-purpose AI account into a much richer target.
- 2026-08-06A fake deodorant reached ChatGPT’s AI shelf. Shopping agents need receipts.
A synthetic deodorant reportedly reached ChatGPT recommendations in 21 days. The stunt is small. The trust problem for shopping agents is not.
- 2026-08-05Open-weight AI is closing the capability gap faster than the safety gap
GLM-5.2 is near frontier cyber capability while a new industry RFC asks for shared incident evidence. Builders now own the controls around the model.
- 2026-08-04The model is becoming a tenant in the customer’s cloud
Superblocks and June point to the same enterprise AI thesis: the durable product is the control plane around a replaceable model.