Phying News
P非影 中文
Curated security research, vulnerabilities, advisories and tools for practitioners.

[CVE-2024-9143] DOMPurify bypasses, prompt injecting ChatGPT to shell, AI fuzz finds – ethical hacker news roundup

yeswehack.com | blog | CVE-2024-9143 | #ai-security | #prompt-injection | #llm-security | #openssl | #oss-fuzz | #dompurify | #roundup

Summary

Roundup: DOMPurify bypasses in default configs through v3.1.2, prompt injection to shell in OpenAI's containerised ChatGPT, and AI-enhanced OSS-Fuzz finding 26 flaws incl. OpenSSL CVE-2024-9143.
Published
Collected

original ↗

Related coverage

  1. What’s changed in AI security over the past two years (bugcrowd.com)
  2. Introducing the Prompt Airlines CTF: Test Your AI Security Skills (wiz.io)
  3. Inside 90 days of attacks on AI infrastructure (wiz.io)
  4. Agentic Problems and the Rise of Zombie AIs (ethiack.com)
  5. Testing AI-powered systems at scale via Bug Bounty, part 3: the guardrails (yeswehack.com)
  6. Rickrolling the World Cup, unleashing AI across Google, 0-click stored XSS on Next.js – ethical hacker roundup (yeswehack.com)

back