Comment-and-Control | GRID THE GREY

LIVE THREATS

HIGH Claude Code, Gemini CLI, GitHub Copilot Agents Vulnerable to Prompt Injection via Comments // MEDIUM OpenAI Widens Access to Cybersecurity Model After Anthropic’s Mythos Reveal // MEDIUM Human Trust of AI Agents // MEDIUM Frontier AI for Defenders: CrowdStrike and OpenAI TAC // MEDIUM Deterministic + Agentic AI: The Architecture Exposure Validation Requires // CRITICAL ‘By Design’ Flaw in MCP Could Enable Widespread AI Supply Chain Attacks // MEDIUM Capsule Security Emerges From Stealth With $7 Million in Funding // HIGH Does Gas Town 'steal' usage from users' LLM credits to improve itself? // HIGH Microsoft, Salesforce Patch AI Agent Data Leak Flaws // MEDIUM What Claude Code's Source Revealed About AI Engineering Culture //

1 report

All LLM Security Industry News Agentic AI Research Supply Chain Regulatory Prompt Injection Adversarial ML Jailbreaks Model Theft

ATLAS OWASP HIGH SecurityWeek Apr 17, 2026 ▲ 8.2

Claude Code, Gemini CLI, GitHub Copilot Agents Vulnerable to Prompt Injection via Comments

A researcher has disclosed a novel prompt injection attack technique dubbed 'Comment and Control,' demonstrating that popular AI coding agents — including Claude Code, Gemini CLI, and GitHub Copilot …

AML.T0051 - LLM Prompt Injection AML.T0043 - Craft Adversarial Data AML.T0047 - ML-Enabled Product or Service