cybercentry-web-application-verification

SUSPICIOUS: the skill’s core behavior matches its stated purpose, but its footprint is high risk. It gives an AI agent offensive web-scanning capability, routes target data to an external paid service, and explicitly encourages forwarding authenticated session cookies to that service. The ACP CLI install path adds moderate supply-chain trust concerns, and the external data retention model is expansive. Not confirmed malware, but risky and disproportionate for unsupervised agent use.