Adversa AI
CompanyRecent news
Adversa AI roundup lists 17 agent skill security resources for November 2026
Adversa AI's November 2026 roundup covers 17 resources on agent skill security. Highlights include an official OpenAI skill that leaked tokens, scanners bypassed through bytecode, and individually clean skills that can be chained together to cause harm.
Roundup of AI coding agent security issues for November 2026
Adversa AI's November 2026 roundup highlights three AI coding agent issues: a remote code execution flaw in Copilot involving a trailing dot, a child Claude session that skips hook consent, and an opencode fix that has no CVE. The article gives no further technical detail, so the scope and affected versions are not stated.