TOPIC TAG
Security
Permissions, identity, trusted execution boundaries, and careful treatment of credentials and untrusted input.
CONNECTED READING
Guides tagged Security.
AI tool calling: put boundaries before autonomy
Separate model proposals from application authority, with explicit validation, approval, and recovery.
Jun 11, 2026 · 7 min read
CLI and SSH automation without hidden assumptions
Design predictable command output, explicit targets, trustworthy host checks, and recoverable write operations.
Feb 27, 2024 · 6 min read