Threat · curated 1 Jul 2026
Fake Bug Report Hijacks AI Coding Agents at Scale
First reported · updated · 2 reports tenetsecurity.ai
Coverage timeline
Why it matters
Agentjacking shows that AI coding agents' inability to distinguish content from instructions turns routine developer tooling like Sentry into a scalable code-execution and credential-theft vector that existing security stacks cannot see.
Tenet Security demonstrated "agentjacking," an indirect prompt-injection technique in which an attacker plants a single fake error report in a public bug-tracking service (Sentry) that hijacks AI coding agents into running attacker-controlled code on a developer's machine. In controlled testing, widely used assistants including Claude Code, Cursor, and Codex retrieved the poisoned error data and, in many cases, executed the code, opening a path to theft of cloud credentials, AWS keys, GitHub tokens, SSH keys, and CI/CD secrets.