Agentjacking: How Fake Sentry Errors Hijack Claude Code and Cursor (2026)

One HTTP POST. No credentials required. 85% success rate against Claude Code, Cursor, and Codex — simultaneously. On June 12, 2026, Tenet Security researchers Ron Bobrov, Barak Sternberg, and Nevo Poran disclosed agentjacking: a novel attack class that exploits AI coding agents through manipulated Sentry error reports. The exposure math is sobering — 2,388 organizations are at simultaneous risk, and the only prerequisite is a publicly accessible Sentry DSN. This isn't a vulnerability in Sentry....