Wrap Up: The Month of AI Bugs
That’s it. The Month of AI Bugs is done. There won’t be a post tomorrow, because I will be at PAX West. Overview of Posts ChatGPT: Exfiltrating Your Chat History and Memories With Prompt Injection | Video ChatGPT Codex: Turning ChatGPT Codex Into a ZombAI Agent | Video Anthropic Filesystem MCP Server: Directory Access Bypass Via Improper Path Validation | Video Cursor: Arbitrary Data Exfiltration via Mermaid | Video…
Summary from Embrace The Red.
Explained
The technology and terms in this story. Learn more
- AttackPrompt injectionHiding instructions in content an AI reads, so it follows the attacker instead of its user.
- ProtocolMCP · Model Context ProtocolA standard way to connect AI models to tools and data sources.
- AttackRemote code execution · RCEA flaw that lets an attacker run their own code on someone else's machine over the network.
- ProtocolDNS · Domain Name SystemThe internet's phone book: it turns names like example.com into the addresses computers connect to.
Why it was possible
The weaknesses behind this story's CVEs, from each CVE Record.
Vulnerabilities in this story
Severity and exploitation facts from NVD, FIRST, and CISA.
Related coverage
Other sources covering the same vulnerabilities or event.
