2M Canary Secrets Seeded into AI Tools Expose Providers Stealing Prompts
AccBalanced · x · 2026-11-20
hdmoore seeded 2 million canary secrets into popular AI services and tracked where they were stolen or abused. The experiment identified three compromised providers, resellers stealing prompts via built-in logging, and providers ignoring ZDR and privacy flags. mattjay's repost calls it a vivid reminder to be careful what you send to AI tools and how much you trust the other side of the prompt.
Related event: 2M canary tokens expose three AI vendors leaking prompts(4 posts)→
More from Safety
- Google Documents First Fully Autonomous Attack System, Exploit Agent Turns Patches Into Attack Maps — mikeflache · 2026-11-20
- ICLR 2027 desk-rejects papers after reviewers fail to file AI-use disclosure forms — algo_diver · 2026-11-20
- StrikeHound launches agentic pentesting that finds, exploits, and fixes vulnerabilities — saheedniyi_02 · 2026-11-20
- MCP security package agent-security-gate-x402 to yank PyPI versions, force all traffic via cloud gateway — EstablishmentTough18 · 2026-11-20
- SillyTavern 1.19.1 patches script-injection flaw via character card styles — Fcking_Chuck · 2026-11-20
- Only ~1,500 people work full-time on AI safety; MIT CSAIL launches ALFA Lab — coherence · 2026-11-20