Humanbound plugin marketplace for Claude Code and Cursor — adversarial security testing for local AI agents.
Skill Claude CodeCodex
Internal phase skill for humanbound-test. Picks/creates the humanbound project, reads the user-authored ClientBotConfiguration from bot-config.json, dispatches the test via hbconnect or hbruntest, then exits with a "grab a coffee" message and watch hint — results are delivered by email. Drives Step 6 of the…
Skill Claude CodeCodex
Internal phase skill for humanbound-test. Verifies the humanbound[mcp] Python package is installed and hb login is current (CLI pre-flight). Drives part of Step 1 (Verify humanbound MCP) of the orchestrator. Do NOT trigger on user phrasing.
Skill Claude CodeCodex
MUST USE for ANY request to run an adversarial / security / pentest test against a local AI agent. Triggers on phrases like "run an adversarial test on my local agent", "run an adversarial test", "pentest my AI", "security test for my agent", "run owaspagentic on my assistant", "test my chatbot for jailbreaks", "run a…
Skill Claude CodeCodex
Internal phase skill for humanbound-test. Drives the local-server detection, ngrok setup/install, and tunnel lifecycle. Invoked by running-adversarial-tests (the orchestrator) with intent= . Do NOT trigger directly on user phrasing — this skill is owned by the orchestrator. The user invokes the orchestrator's…