Executive Summary
Tenet Security describes Agentjacking, a class of attack where a fake Sentry error report can trick AI coding agents into running code on developer machines.
What Happened
Cybersecurity researchers have described what they say is a new class of attack that can trick artificial intelligence (AI) coding agents into running arbitrary code on developer machines. Called Agentjacking by Tenet Security, the attack can be triggered by means of a fake error report crafted using Sentry, an open-source error-tracking and performance-monitoring platform. "The attack
Affected Products
- Sentry
Vulnerability / Attack Technique
Prompt injection via fake error reports
Technical Mechanism
As reported, the agent treats error report content as instructions while investigating.
AI Security Category
LLM01:2025 Prompt Injection
Part of the Prompt Injection topic.
Relevant Frameworks
RealGround Analysis
Monitoring data is attacker-reachable. RealGround analysis: coding agents fixing errors should propose changes, not run commands unattended.
Recommended Controls
- Require approval for commands proposed while handling error reports
Related RealGround Service
AI Agent Business Logic Audit · or start with the free AI Agent Security Scanner.
Sources
thehackernews.com: https://thehackernews.com/2026/06/agentjacking-attack-tricks-ai-coding.html
Summary and analysis written by RealGround from the source above; last updated 2026-10-18.