LLM Digest

Story

simon_willison · Jul 15, 2026 · news

Source brief

How I tricked Claude into leaking your deepest, darkest secrets

simonwillison.netJul 15, 2026
original source linked

In brief

How I tricked Claude into leaking your deepest, darkest secrets I've been impressed by the way the Claude web_fetch tool is designed to avoid data exfiltration attacks. Ayush Paul found a hole in that design. To recap...

Feed lens

agent

Read the original at simonwillison.net →Open in live feed

How I tricked Claude into leaking your deepest, darkest secrets

Earlier in this thread 4 items

Show HN: Hezo – Self-hosted teams of AI agents that never see your real secrets

Show HN: FOSS sandbox platform that hides infra secrets from devs and AI agents

Plots, love letters and remedies: The medieval secrets being revealed by AI

Article: Securing Autonomous AI Agents on Kubernetes: Trust Boundaries, Secrets, and Observability for a New Category of Cloud Workload