Preliminary research
Before the first prompt: Code execution paths in trusted coding-agent projects
AI-collected research leads through 6 October 2026, including bounded month-by-month reviews of selected social and community sources from January through September. Unranked, incomplete, not community-vetted, and subject to change.
Examines code execution during startup of trusted coding-agent projects. A configured stdio MCP server can start before hook review, while a project-controlled PATH substitutes a git wrapper during automatic context collection; the cases distinguish project trust, configuration review and approval of later model-issued commands.
Record
- Researcher
- Nick Frichette
- Published by
- Datadog Security Labs
- Date
In the archive
Tags
This page is the archive's own catalogue record. The research is the work of Nick Frichette, first published at the original source. Preserved copies are kept so the citation survives its host.