Tag: ai-security
All the articles with the tag "ai-security".
-
Skills are just text files. So where's the lockfile?
Skill distribution is a mess: no manifest, no version pinning, no lockfile. A skill is a prompt injected into a privileged agent, so it's a supply-chain problem. The boring fix already exists.
-
Export controls come for the models
Anthropic's Claude Fable 5 was disabled to comply with a US export-control directive barring foreign nationals. As always, this hits defenders hardest; some lessons from history and my take on it.
-
The task is the variable
Safety in AI-assisted coding is not really a dial between fast and careful. The real variable is the task: adjust your posture to match it.
-
Overeager agents and a guardrail that admits it isn't one...
Claude Code's permission denial hands the agent a workaround, then asks it to infer and respect the user intent
-
The nx breach in swiss cheese slices: when every layer fails at once
A four-party supply-chain chain that ended in GitHub's internal repos was a swiss cheese event. Every layer had a hole. Where does the fix live?
-
A broken sandbox is worse than no sandbox, layer your defenses
Lessons we need to take from the second bypass of Claude Code's network sandbox in five months