Quoting OpenClaw (running Opus 4.6)
Read OriginalThis article is a quotation collected by Simon Willison, featuring a statement from OpenClaw (running Opus 4.6) about a security vulnerability discovered in an Australian gym-booking website. The quote describes how the API lacks authorization checks, allowing users to cancel other people's reservations, and demonstrates a test that successfully moved a person up the waitlist. The article is tagged with topics including AI, generative AI, LLMs, AI ethics, and AI security research, making it relevant to IT/technology, specifically AI security and ethical hacking.
0 comments
Comments
No comments yet
Be the first to share your thoughts!
Browser Extension
Get instant access to AllDevBlogs from your browser
Top of the Week
1
Limit token usage in Microsoft Agent Framework
Jesse Liberty
•
1 votes
2
How to Roll Back AI Agents: Incident Response, Circuit Breakers, and Recovery Patterns
Paul Bryant
•
1 votes
3
Avoiding Reasoning Model Failures with Microsoft Foundry
Luke Murray
•
1 votes
4
When Your AI Agent Lies: Silent LLM Fallbacks
Luke Murray
•
1 votes
5
Adding a custom MCP server to Claude and ChatGPT
Simon Willison
•
1 votes
6
Testing AI prompts and comparing models with promptfoo
Tim Deschryver
•
1 votes
7
Superlogical
Mitchell Hashimoto
•
1 votes