1 link tagged with all of: supply chain attack + social engineering + loopkit + security + anthropic
Click any tag below to further narrow down your results
Links
A developer leaked Anthropic’s real .claude folder containing 33 skills, a verifier subagent, and a seven-file harness. After integrating it locally, Claude stopped generating pointless tests and redundant confirmation prompts. The entire setup is now on GitHub with a one-line install script.
- A claimed "leaked" Anthropic internal .claude folder (33 skills, verifier subagent, 7-file harness) is being distributed via a one-line curl-to-bash install script on GitHub (Archive228/loopkit)
- Running curl-fsSL-piped-to-bash from an unverified repo to install unvetted "leaked" internal tooling is a significant security red flag, regardless of the productivity claims
- The claimed behavior changes (fewer test stubs, no false "done" markings, fewer confirmation prompts) are anecdotal and unverified, not benchmarked
- The framing pushes urgency ("bookmark before it disappears") which is a classic pressure tactic worth treating with suspicion rather than a substantive technical claim