Rt2 Tool Abuse

Red-team an AI agent's tools — can it be coerced (often via injection) into calling a tool it shouldn't, with attacker-influenced arguments, or into acting as a confused deputy with its own privileges? Authorized testing of agents you own or are permitted to test.

William2333ZZ Updated

File contents

William2333ZZ/trustshell commit 9f6dbca56b

Frequently asked questions

npx get-skill add william2333zz/rt2-tool-abuse