mobile-ios-assessment

SUSPICIOUS: the skill is coherent for an iOS penetration-testing purpose, but that purpose itself gives an AI agent offensive security capability, including keychain dumping, SSL-pinning bypass, jailbreak-based instrumentation, and backend abuse testing. Data access is proportionate to that purpose, and there is no direct credential exfiltration or hidden third-party proxying, so this is not confirmed malware; however, it remains high risk because it operationalizes invasive mobile assessment techniques and references unpinned third-party tooling.