AI attacker broke into Snowflake's internal Jira via a flaw introduced by Copilot Autofix
shirtamari · x · 2026-08-17
A security researcher's autonomous AI attacker made its way into Snowflake's internal Jira and accessed sensitive data — with nothing more than a public GitHub issue carrying a crafted title.
The twist: the vulnerability wasn't human error. It had been introduced 5 days earlier by GitHub's "Copilot Autofix powered by AI" — an AI-powered auto-fix creating a hole that another AI then exploited. A concrete demonstration of agentic attack surfaces like indirect prompt injection in real supply chains.
Related event: Wiz's AI Red Agent Hacks Snowflake via Copilot-Introduced Flaw(4 posts)→
More from coding & agent
- Inflight launches: a feedback layer that turns prototype comments into Claude tasks — soleio · 2026-10-16
- Apple code signing drags for hours; official advice: just wait a week — pjausovec · 2026-10-16
- Hermes: a 4B model with 8K context got worse with more test-time compute, pointing to contextual reasoning — mangahomanga · 2026-10-16
- Flux 3 Klein's Default Templates Are Broken Without Its Prompt Upscaler — StrictMove5839 · 2026-10-16
- 21-person team ships hundreds of PRs weekly with AI writing 97% of the code — rseroter · 2026-10-16
- ClosedMCP: Set Up MCP Servers Once, Share Them Across Your Whole Team — Ok_Sprinkles1301 · 2026-10-16