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: Wiz's AI Red Agent Hacks Snowflake via Copilot-Introduced Flaw(4 posts)→
More from coding & agent
- Dispatch launches newsletter infrastructure built for AI agents, one API call to publish — RichardsonDx · 2026-10-16
- Hyperbrowser launches macOS sandboxes giving agents desktop, apps and Terminal control — madhavsinghal_ · 2026-10-16
- Creator shares the agent-powered system behind millions of monthly impressions — VibeMarketer_ · 2026-10-16
- Devs say LLM coding mistakes are a different class: overcomplication, inferred limits, worse at higher reasoning — Mu5_ · 2026-10-16
- How do you debug bad agent runs when you already have tracing? — Sensitive-Parsnip-12 · 2026-10-16
- Where does pre-task context live for agents? Devs debate workflows beyond handoff — shishen2026 · 2026-10-16