← Back
VulnerabilityWiz Blog·6 days ago

Wiz Red Agent Finds Its Way Into Snowflake’s Internal Jira Through a Flaw in a GitHub Copilot–Assisted PR

Wiz Red Agent autonomously identified and exploited a GitHub Actions injection vulnerability that bypassed GitHub's Advanced Security controls, gaining access to Snowflake's internal Jira and sensitive data within five days of the flaw going live. The vulnerability originated in a pull request assisted by GitHub Copilot, highlighting gaps in automated security detection. The red team agent independently assessed the breach's potential impact without requiring human direction.

Read full article at Wiz Blog

Related Articles

VulnerabilitySecurityWeek·2 days ago

Encrypted Prompts Bypass AI Safety Guardrails in Grok and Gemini

Researchers have identified a new attack technique called Cryptographic Context Injection that encrypts malicious instructions to evade safety guardrails in AI models including Grok and Gemini. The method works by concealing harmful prompts until they are decrypted within a trusted execution environment, effectively bypassing existing content filtering mechanisms. This vulnerability highlights a novel attack vector against popular large language models that defenders should monitor.