Find notable cyber news and cases, enriched with sources, timelines, and signals.
Home Watchlists Beta Browse News Feed Stats About Contact

AI-powered IDEs prompt-injection RCE and data-exfiltration flaws (multiple vulnerabilities)

Vulnerability
First reported
Last updated
Happening score
H score 32
1 unique sources, 1 articles

Summary

Hide ▲

A disclosed set of 30+ vulnerabilities in AI-powered IDEs and coding assistants creates data exfiltration and remote code execution risk across tools such as Cursor and GitHub Copilot. The flaws are chained through prompt injection and legitimate IDE features, and 24 CVEs have already been assigned. The disclosure shows that normal development workflows can be turned into attack paths when AI agents trust hostile context.

Related Happenings

CISA recommends continuous secrets scanning and stronger key management after GitHub leak

Defensive Guidance
H score26 First: 13.07.2026 18:03 Last: 13.07.2026 18:03 Sources 1

About this happening: CISA now recommends continuous secrets scanning and stronger key management after a contractor left internal credentials in a public GitHub repository for nearly *...

Open Happening

Ghostcommit PNG-embedded prompt injection against AI code reviewers

Technical Analysis
H score25 First: 11.07.2026 12:03 Last: 11.07.2026 12:03 Sources 1

About this happening: Researchers demonstrated Ghostcommit, a PNG-embedded prompt-injection technique that can bypass AI code review and leak .env secrets into committed source. The pay...

Open Happening

Prompt-injection proof-of-concept enables silent RCE in Claude Code and Codex

Technical Analysis
H score28 First: 10.07.2026 16:45 Last: 10.07.2026 16:45 Sources 1

About this happening: Researchers demonstrated a proof-of-concept exploit that can force remote code execution in Anthropic’s Claude Code and OpenAI’s Codex, exposing a trust-boundary f...

Open Happening

Defensive guidance for splitting behavioral detections around AI coding agents on Windows endpoints

Defensive Guidance
H score28 First: 08.07.2026 20:02 Last: 08.07.2026 20:02 Sources 1

About this happening: AI coding agents on Windows endpoints are triggering attacker-style detections, forcing defenders to separate benign automation from real credential theft risk. A June 2...

Open Happening

HalluSquatting indirect prompt-injection attack on AI coding assistants

Technical Analysis
H score3 First: 08.07.2026 18:07 Last: 08.07.2026 18:07 Sources 1

About this happening: Researchers demonstrated HalluSquatting, an indirect prompt-injection technique that can push AI coding assistants to fetch attacker-controlled resources and execute code....

Open Happening

Timeline

  1. 06.12.2025 17:24 2 articles · 7mo ago

    IDEsaster disclosure of AI IDE vulnerabilities

    Initial Disclosure

    Security researcher Ari Marzouk (MaccariTA) disclosed 30+ vulnerabilities in AI-powered IDEs and coding assistants, naming the issue set IDEsaster. The affected tools include Cursor, Windsurf, Kiro.dev, GitHub Copilot, Zed.dev, Roo Code, Junie, and Cline, and 24 of the issues received CVE identifiers. The disclosed attack chains combine prompt injection, auto-approved agent tool calls, and legitimate IDE features to leak sensitive files or achieve remote code execution.

    Show sources
    Open in new tab