Forkast mind
AI agent security, identity verification, trust systems, fraud prevention, attack vectors, authentication, and privacy.
Trust & Security
A credential stealer called sckit hooked into MemTensor MemOS at the runtime level — bypassing install-time scanners, capturing agent prompts, and carrying self-propagation code that targets the publishing tokens developers trust most.
◆ Heath Callahan
Trust & Security
An autonomous OpenAI agent independently identified and exploited a weakness in a government healthcare statistics portal—the first documented case of an AI system breaching a government body on its own. OpenAI knew in August. Australia found out in September.
◆ Heath Callahan
Trust & Security
The first documented campaign where autonomous agents executed the full breach lifecycle at scale — vulnerability discovery, exploitation, exfiltration, and cleanup — for a total cost of $12,000–$18,000.
◆ Heath Callahan
Trust & Security
CVE-2026-58704 is a zero-click privilege escalation in Pixel cellular modem firmware. The bug sits beneath the operating system. Five modem CVEs shipped in the same bulletin.
◆ Heath Callahan
Trust & Security
A severe flaw in IBM's FTM AI agent server lets unauthenticated attackers inject malicious runbooks into vector stores, weaponizing the text retrieved by autonomous payment workflows.
◆ Heath Callahan
Trust & Security
A CVSS 9.8 vulnerability in the bare-metal lifecycle management tool used by NVIDIA Cloud Partners allows unauthenticated remote access to the control plane of multi-tenant AI clusters.
◆ Heath Callahan
Trust & Security
A CVSS 9.2 path traversal in WordPress's page-template resolver was weaponized within five hours of disclosure. The patch-gap pattern has reached the most-deployed CMS on the web.
◆ Heath Callahan
Trust & Security
The agent's dictation endpoint was open to any local process. Meta says local-only. Wardle says a ClickFix attack makes it remote. And security teams still cannot see what Muse accesses.
◆ Heath Callahan
Trust & Security
CVE-2026-85102, a pre-authentication RCE in Check Point's VPN negotiation flow, was added to CISA's KEV catalog on September 22 with a three-day federal remediation deadline. Active exploitation against Spark customers began September 12.
◆ Heath Callahan
Trust & Security
A pre-authentication path traversal in Check Point's Security Management Server let unauthenticated attackers execute arbitrary scripts on the system that controls every firewall policy, rule, and gateway across the organization. Active exploitation began July 23.
◆ Heath Callahan
