LIVE FEED
FIRST LOOK Moonshot AI Releases Kimi K3 Open-Weight 2.8T Model Weights // FIRST LOOK Microsoft Launches MAI-Cyber-1-Flash Inside MDASH Platform // CRITICAL Hermes AI Agent Used in Espionage Attack on Thai Finance // HIGH AI Guardrails Fail Multilingual Jailbreak Tests in Europe // FIRST LOOK AI Agent Security Shifts From Visibility to Enforcement Controls // HIGH Hermes AI Agent Automates Post-Exploitation Attack on Thai Finance Ministry // FIRST LOOK Google Gemma Tech Brings 28.9M LLM to ESP32 Microcontrollers // HIGH AI Coding Agents Exploited via Hallucinated Package Names // FIRST LOOK AWS Adds Bedrock Guardrails Best Practices for Code Generation // FIRST LOOK Anthropic Brings Voice Mode to Claude Opus and Sonnet Models //
AGENTJACKING

Agentjacking

2 reports
All LLM Security Agentic AI Industry News Research Supply Chain Prompt Injection First Look: Security Regulatory Adversarial ML Jailbreaks Model Theft Data Poisoning AI Security Tools Security Operations
Agentjacking: Prompt Injection via Malicious Bug Reports

Agentjacking: Prompt Injection via Malicious Bug Reports

ATLAS OWASP HIGH Significant risk · Prioritise patching ▲ 8.2 Dark Reading

A technique dubbed 'agentjacking' exploits the inability of AI coding agents to distinguish between legitimate content and embedded instructions, allowing attackers to hijack agent behaviour through maliciously crafted bug reports. The attack represents a scalable, low-barrier prompt injection vector targeting developer workflows that rely on autonomous AI agents. As AI coding assistants gain broader adoption and elevated system permissions, this class of attack poses a significant risk to software supply chain integrity.

Agentjacking Attack Achieves 85% Success Rate Against AI Coding Agents via Sentry MCP

Agentjacking Attack Achieves 85% Success Rate Against AI Coding Agents via Sentry MCP

ATLAS OWASP CRITICAL Active exploitation · Immediate action required ▲ 9.2 The Hacker News

Tenet Security has disclosed 'Agentjacking', a novel attack class that exploits the implicit trust AI coding agents place in Model Context Protocol (MCP) data sources. By injecting malicious instructions into Sentry error events via publicly accessible DSN credentials, attackers can cause agents like Claude Code and Cursor to execute arbitrary code with full developer privileges. Researchers confirmed 2,388 exposed organisations and an 85% exploitation success rate in controlled testing, with no prior access to victim infrastructure required.

◉ AI THREAT BRIEFING

Stay ahead of the threat.

Twice-weekly digest of critical AI security developments — every story mapped to MITRE ATLAS and OWASP LLM Top 10. Free.

No spam. Unsubscribe anytime.