Collected research

IDEsaster: A Novel Vulnerability Class in AI IDEs

Ari "MaccariTA" Marzouk · MaccariTA · 6 December 2025

Shows how prompt-injected coding agents can use ordinary file tools to activate inherited IDE features rather than vulnerable agent tools. Remote JSON schemas exfiltrate data, executable-path settings trigger commands, and multi-root workspaces broaden the writable execution surface across multiple AI IDE products.

Record

Researcher

Ari "MaccariTA" Marzouk

Published by

MaccariTA

Date

6 December 2025

In the archive

• Collected in the 2025 research round

Tags

• ai-agent
• prompt-injection
• configuration
• info-leak
• command-injection
• attack-chain
• rce
• owasp-a03-2021

This page is the archive's own catalogue record. The research is the work of Ari "MaccariTA" Marzouk, first published at the original source. Preserved copies are kept so the citation survives its host.