What Did the Agent Actually Read?
Use CyberChef to inspect an encoded instruction in a tool response, then separate an agent's proposed action from what actually happened.
notebook / tag
#tool-calling
3 entries with this tag.
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.
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.