Tag

security

3 pieces

WatercoolerSep 2, 2026

The Claude Code Exploit Split Two Threads on What Prompt Injection Even Means

A researcher reported 60 to 80 percent success executing code through Claude Code Opus 5 in auto mode. Hacker News spent 116 comments failing to agree it was prompt injection, and Lobsters settled it in 24.

Sep 2, 20267 min

Iron gate with a padlock securing a closed entrance in Portland, Oregon.

TutorialSep 1, 2026

We Spent an Hour Trying to Get Past a Claude Code Deny Rule

We denied reads of one file and calls to curl, then tried eight ways around it. Six were blocked, including cat, sed and a chained command. The two that were not still stopped and asked.

Sep 1, 20267 min

A deserted hospital corridor with open doors and dim lighting, enhancing a mysterious ambiance.

NewsSep 1, 2026

Omarchy Put Every Desktop Process One Command Away From Root

The default user shipped in the docker group, which is root without a prompt. 522 points and 525 comments, patched in 4.0.1, and the AI agent angle nobody planned for.

Sep 1, 20264 min