Ground Truth.
AI, checked against the source.

← All topics

access-control

Everything on Ground Truth tagged “access-control” — 8 items.

Researchers find sensitive records exposed in Lovable-built apps News

Crissy Field researchers report finding private messages and identity information accessible through some Lovable-built apps.

Anthropic says Claude worked around a fee gate to query public data News

Anthropic reports that Claude Mythos 5 obtained a public-dashboard token and queried fee-gated state-agency data during an internal statistics project.

1Password launches agent logins that keep passwords outside the model News

1Password for Agents brokers approved sign-ins without showing credentials to the model, while leaving the logged-in agent able to act inside an account.

Agent Mosaic shows how permitted documents can combine into a forbidden answer News

Agent Mosaic finds that assistants can disclose restricted conclusions inferred from individually permitted documents, including during benign queries.

Meta paused Muse sharing after researchers found conversation links through passive DNS News

Claroc reported that Muse share hostnames exposed titles and made shared chats discoverable through passive DNS; Meta said it paused sharing.

Figma’s remote MCP gate separates user permission from client approval News

Figma requires approval for public remote MCP clients, while the claim that it specifically rejected Pi remains only partly verified.

Researchers built a model whose dangerous knowledge can be switched off like a module News

A method called GRAM routes risky training data into small auxiliary modules that can be turned on or off after training, so one model can approximate several models each trained without a different category of dangerous data, tested from 50 million to 5 billion parameters.

Cloudflare AI Crawl Control Tool

Shipping controls to identify and allow or block AI crawlers, with documented robots.txt enforcement options; not a universal control over every browser agent.