anthropic-toolkit

MAL-2026-6673

npmtyposquat6/30/2026
Description

Malicious code in anthropic-toolkit (npm)

Indicators of Compromise
SHA256 Hashes (21)
047000077a5181c5394d7caec1a5d27e71dc984396e951e2b83985b1f9b20989
49b0519f55b08c13567aec6a38dc2a7e0226d22a37885c86e609f03f7e99eaee
4a3490eb87ca9c29a8febbb5e5a13ff067cce445eb4ddccaefd462a067da0742
65a6ab4cc1aa0cb57baa92acaf3ee25793f33ba8ab053a9eb065c7692723dfca
6eff9920c4daa41936562f9a40baf01463fa50ce81f28ff9b0750fd157f4aec6
93f1e4b3b2d59ed3c4961ded435de21add69b43492ec5d12b625a9b6c50edc72
bcb08c0e2f8d02016153046061d99e4956ea06f8a3e7ec032863c35b639c394e
c8ef319a04814111a56265898f4441a094c31af07f27e8799c36d8323888cc8c
da8c70a3ea2062cc2675d513e63ee119544895d9ebffa72a255b83326a66527f
90ec82c6478e3a82eac71597b1c1fffc17d1b138e11e1a2aeadec7c00344c65e
Details
Ecosystemnpm
Attack Typetyposquat
Published6/30/2026
Agentic AI · Pentesting

Ready for Agentic Automated Testing?

Deploy autonomous AI agents that reason, exploit, and validate complex vulnerability chains — not another scanner, an agentic system that thinks like a senior pentester.

Zero false positives
PoC for every finding
30+ tools orchestrated
Setup in 5 minutesSOC 2 & ISO 27001