humanbound

12 mods across 2 repositories, 144 stars between them.

humanbound-test

02

humanbound/plugins

Plugin Claude Code

Run adversarial / security tests against your local AI agent. Detects your FastAPI server, exposes it via ngrok, you author bot-config.json with your endpoints / auth / payload, the plugin dispatches via the humanbound MCP — results delivered by email (or run /humanbound-test:resume to watch the polling loop and f.

14 1mo ago A tokens not measured

config

03

humanbound/plugins

Command

View or edit the project's .humanbound/test/config.toml interactively.

14 1mo ago A 14 tokens

resume

04

humanbound/plugins

Command

Resume polling a previously-started experiment by ID.

14 1mo ago A 9 tokens

run

05

humanbound/plugins

Command

Run an adversarial test against the local agent (full flow).

14 1mo ago A 13 tokens

setup

06

humanbound/plugins

Command

One-time setup — install humanbound[mcp], log in, install + auth ngrok.

14 1mo ago A 18 tokens

status

07

humanbound/plugins

Command

Show running tunnels and active experiments for this project (or all).

14 1mo ago A 13 tokens

stop

08

humanbound/plugins

Command

Stop the tunnel for this project (idempotent).

14 1mo ago A 11 tokens

humanbound/plugins

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…

14 1mo ago A 0 tokens

humanbound/plugins

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.

14 1mo ago B 66 tokens

humanbound/plugins

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…

14 1mo ago A 173 tokens

humanbound/plugins

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…

14 1mo ago A 85 tokens