notebook / tag

#tool-calling

2 entries with this tag.

Aug 17, 2026 / 9 min / agentic-ai

Prompt-Injection Testing Belongs in CI

ToolHazard turns indirect prompt-injection testing into executable, stateful evaluation. The useful lesson is not its leaderboard. It is how to make agent security a repeatable release gate.

#aisecops #agent-security #evaluation #prompt-injection

Jun 14, 2026 / 2 min / research

A Small Pattern Library for Tool-Calling Agents

Four simple work patterns for agents that use tools, make changes, test the result, and recover from interruptions.

#tool-calling #patterns #evals #agents