Run authorized AI-assisted pentest and remediation workflows with RedAmon
Map an approved attack surface, run recon and exploitation from a Kali sandbox, triage findings, and open remediation pull requests with human approval gates.
npx skills add agentskillexchange/skills --skill run-authorized-ai-assisted-pentest-and-remediation-workflows-with-redamon
Use RedAmon when a security operator has written authorization to test a target and wants an AI-assisted workflow that chains reconnaissance, exploitation, post-exploitation evidence, triage, and code-fix pull requests. Invoke it instead of using the web app manually when an agent should coordinate the approved test plan, inspect the attack-surface graph, call MCP tools, and hand off findings or fixes through review gates. The scope boundary is authorized security assessment and remediation against assets the operator is allowed to test; it is not a general hacking toolkit listing, scanner roundup, or unsupervised offensive automation card.
What this skill actually does
Inputs and prerequisites: Docker, Docker Compose v2, RedAmon stack, optional GVM/OpenVAS, configured AI provider keys, and explicit authorization for every target.
Setup notes: Clone https://github.com/samugit83/redamon, run ./redamon.sh install for the lighter stack or ./redamon.sh install –gvm for the full OpenVAS stack, create the admin account when prompted, configure approved targets and provider keys, then use the MCP or Claude Code integration only within authorized testing scope.
Source and verification boundary: use https://github.com/samugit83/redamon/wiki as the canonical reference before running the workflow; keep commands, API calls, CLI usage, and generated outputs reviewable against that upstream source.
Framework fit: publish this as a MCP workflow only when the operator can invoke the documented toolchain directly, rather than treating the upstream project as a generic product listing.