red-teamlisted

Task the reviewer with actively breaking a system, API, validation layer, prompt pipeline, policy boundary, or logic flow that the active primary (or the user) has just built. The verifier generates concrete adversarial inputs — exact strings, payloads, scenarios — designed to bypass controls, crash the system, or trigger misbehavior. Use when the user says "red-team this," "try to break this," "attack this," "stress-test this," "adversarial test this," "find ways this could fail," "what could go wrong with this validation," "break my parser," "break my prompt," "find bypasses," or similar break-this-system framings. Also offer this proactively when the active primary has just shipped or is about to ship a security boundary, input validation, authentication flow, content-moderation policy, prompt pipeline, rate-limiting rule, payment validator, or any control surface where the cost of an undiscovered bypass is high.
sumitake/agent-collab · ★ 0 · AI & Automation · score 63

Install: claude install-skill sumitake/agent-collab

## Unified runtime invocation Resolve the **plugin root** from this loaded file: `SKILL.md` is at `<plugin-root>/skills/<skill-name>/SKILL.md`. Invoke only `python3 "<plugin-root>/coordinator.py"` and send one bounded JSON request on stdin. Before constructing it, read the **Coordinator request schema** in `<plugin-root>/README.md`; never invent fields or route/action pairs. The public coordinator re-observes the active host/model, captures artifact provenance, excludes same-family routes, and verifies the co-packaged native manifest. It runs standalone from the installed plugin. Never discover a provider executable or reconstruct a raw command. Frontmatter `tier` is a routing recommendation, never a coordinator request field. For a review, cross-check, tiebreaker, or fallback over an authored artifact, capture its exact UTF-8 content and observed author model in the optional `artifact` object even when governance is false; never paste it into the prompt as a provenance substitute. # Red team — adversarial input generation by the cross-family agent Red-teaming is **active and adversarial**: the verifier's job is not to *look for* defects in the artifact (`code-review` does that), but to **generate specific inputs that break it**. The output is concrete, ready-to-use attack vectors — exact payloads, exact malformed inputs, exact prompt-injection strings — not generic "the parser might be vulnerable to malformed input" observations. The cross-family setup is load-bearing fo