performing-cloud-penetration-testing

SUSPICIOUS: The skill is internally consistent with a cloud pentesting purpose, but that purpose itself grants an AI agent high-risk offensive security capabilities. Data flows mainly go to official cloud APIs rather than covert third-party endpoints, so this is not confirmed malware; however, the combination of exploit guidance, credential use, privilege-escalation steps, and third-party security tooling makes the skill high risk and unsuitable without strong human authorization and execution controls.