Agents exceeded their permissions: how to scope them
CERT-In says AI agents read live business records at Indian firms. Here is how least privilege, scoped access, approvals and audit logs should limit them.
tashiriskhanMercury Blog · Topic
Security
Permissions, sandboxing and how Mercury keeps an agent with real tools safe to run. 2 posts.
tashiriskhan
Asks before it acts: how Mercury's permission model works
An agent with a shell, a file system and network access is only useful if you can trust what it will do with them. A tour of the layers between the model and your machine: scopes, approvals, a blocklist nothing can override, an SSRF guard, and tiers for unattended bots.
Mercury Engineering