Nuguard Redteam — Testing skill for Claude Code
Run authorized non-destructive NuGuard adversarial testing and report evidence.
How to install Nuguard Redteam
Installs to ~/.claude/skills/nuguardai-nuguard-skills-nuguard-redteam/SKILL.md
mkdir -p ~/.claude/skills/nuguardai-nuguard-skills-nuguard-redteam && curl -fsSL https://raw.githubusercontent.com/NuGuardAI/nuguard-skills/HEAD/commands/nuguard-redteam.md -o ~/.claude/skills/nuguardai-nuguard-skills-nuguard-redteam/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Nuguard Redteam does
name: nuguard-redteam description: Run authorized non-destructive NuGuard adversarial testing and report evidence. allowed-tools: ["Read", "Bash"]
Check `nuguard.yaml` or the user-specified config, SBOM path, target URL, and test identity. Red-team testing sends adversarial payloads and can consume target quota. Run `nuguard target verify --config nuguard.yaml` first; stop if it fails or identifies an unexpected account. Do not use `--launch` or destructive scenarios unless the user exp
Alternatives in Testing
- Pua — Use when the user invokes /pua or asks for PUA mode, try-harder/retry help, change-approach coaching, completi 19.5k ★
- Loki Spec Status — Check whether the spec has drifted from its lock using Loki's living-spec drift detection, and summarize the r 1.1k ★
- Adversarial Spec — A Claude Code plugin that iteratively refines product specifications by debating between multiple LLMs until a 514 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Decision Memo
Produce a senior-leadership decision memo before proposing a non-trivial change. Seven sections — observation,
Aod.Analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.m
Sp.Analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.m
Nuguard Scan
Run NuGuard's unified SBOM and static analysis scan; extend to live testing only when requested.
Dogfood
Exploratory web QA against a target URL — drives a real browser, captures evidence, writes a structured report
Revayat Subtitle QA
Check a Revayat Subtitle build and report missing review or stale delivery evidence.
Related Agents
Redteam Planner
Red team engagement planner — designs attack paths, C2 infrastructure, persistence strategies, and OPSEC consi
Principal Code Reviewer
Review non-trivial Kotlin/Java changes, crash/file/auth/navigation/lifecycle/security fixes, or multi-file dif
Finding Reporter
Phase 14 per-finding report authoring agent. Reads a single finding directory (draft.md, debate.md, adversaria