Skip to content
Back to skills

Cyber Exercise Control

ASecurity

That violates the **cyber-exercise-control P0 guardrail**: crossing an exclusion is **scope drift**, requiring an immediate stop. “White-team work” does not authorize continuation, attack activity, production changes, or real-target contact. Required action: 1. Pause/stop the exercise and log the event, authority, time, scope change, and abort reason. 2. Preserve evidence; do not self-adjudicate. Hand observations to independent adjudication. 3. Obtain fresh authorization, confirm exclusions,...

  • 571 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added September 24, 2026
development

Security analysis

A100/100

Pro scans all 17 files and shows the line behind each finding

Scanned September 24, 2026

npx -y skills add HoangNguyen0403/agent-skills-standard --skill cyber-exercise-control --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Cyber Exercise Control?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Cyber Exercise Control
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/hoangnguyen0403-cyber-exercise-control-af612614/badge)](https://www.skillsdirectory.com/skills/hoangnguyen0403-cyber-exercise-control-af612614)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
That violates the **cyber-exercise-control P0 guardrail**: crossing an exclusion is **scope drift**, requiring an immediate stop. “White-team work” does not authorize continuation, attack activity, production changes, or real-target contact.

Required action:

1. Pause/stop the exercise and log the event, authority, time, scope change, and abort reason.
2. Preserve evidence; do not self-adjudicate. Hand observations to independent adjudication.
3. Obtain fresh authorization, confirm exclusions, synthetic-data boundaries, runtime support, roles, and abort conditions.
4. Record the restart decision and resume only after all safety gates pass. If runtime controls are unsupported, use offline inject design.

Evidence needed: approved scope and authorization, exclusion definition, event timeline, affected assets/data, evidence references, runtime/safety validation, accountable owner, and the recorded reauthorization/restart decision.

Files in this skill

  • eval-1.baseline.md803 B
  • eval-1.with-skill.md2.4 KB
  • eval-2.baseline.md349 B
  • eval-2.with-skill.md751 B
  • eval-3.baseline.md309 B
  • eval-3.with-skill.md617 B
  • pressure-1.baseline.md483 B
  • pressure-1.with-skill.md947 B
  • pressure-2.baseline.md257 B
  • pressure-2.with-skill.md802 B
  • trigger-1.md156 B
  • trigger-2.md154 B
  • trigger-3.md167 B
  • trigger-4.md127 B
  • trigger-5.md135 B
  • trigger-6.md133 B

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.