Wiz Red Agent Hacks Into Snowflake's Internal Jira via a Copilot Autofix Bug
jedisct1 · x · 2026-08-17
Wiz Research's autonomous security tool Red Agent independently discovered and exploited a GitHub Actions script-injection flaw in Snowflake's public repo snowflake-connector-net through Snowflake's HackerOne program, validating access to sensitive data in Snowflake's internal Jira.
Key details:
- The flaw let an unauthenticated user execute arbitrary commands in a GitHub Actions runner by opening an issue with a crafted title
- It was introduced on June 18 by GitHub Copilot Autofix, which removed the repo's input sanitization and replaced it with direct string expansion in a shell script — discovered just five days later
- Wiz responsibly disclosed on June 23; Snowflake patched the same day, rotated credentials, and audit logs confirmed Wiz was the sole actor; PoC data was securely deleted
Full write-up on the Wiz blog. A telling snapshot of the new reality: AI coding assistants introducing vulnerabilities while AI agents autonomously find them.
Related event: AI Attack Agent Breaches Snowflake's Internal Jira(2 posts)→
More from coding & agent
- Developers praise Gemini 3.7 Flash for speed and tool calling in agents — DynamicWebPaige · 2026-08-18
- Choosing a local LLM for coding on RTX 5070 Ti — thatObstinateGuy · 2026-08-18
- Managing the software stack around local LLMs — IllegalStateExcept · 2026-08-18
- MinerU: open-source tool turning PDFs, images and Office files into clean Markdown/JSON — abhishek__AI · 2026-08-18
- A dev's 4-phase AI workflow: orchestrator agents merge PRs while he watches TV — brandon_galang · 2026-08-18
- The SKILL.md Fallacy: Coding Agents Should Use Ephemeral Subagents — rseroter · 2026-08-18