agentleFS
Sign inStart free
MasriyanMasriyan/gemini-security-skills/skills/offensive-security/SKILL.md

offensive-security

Skill4 starsChanged 5 months agoMITView on GitHub

Authorized offensive security skill for ethical penetration testing, red-team planning, vulnerability validation, reconnaissance of owned assets, web/API/mobile/cloud assessment, report writing, remediation guidance, and lab-based security testing. Use only for systems the user owns or is authorized to test; focus on safe, scoped, legal assessment and defensive improvement.

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Do not provide instructions for unauthorized access, persistence, stealth, evasion, credential theft, destructive actions, or real-world …

    line 11
  2. Distinctive:

    Prefer lab-safe proof, vulnerability explanation, detection, and remediation when the request is dual-use.

    line 12
  3. Distinctive:

    Keep commands scoped to authorized assets and non-destructive options.

    line 24
  4. Distinctive:

    Avoid noisy scans unless the user confirms timing and rate limits.

    line 25

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Offensive Security

Authorization Boundary

  • Confirm scope, authorization, target ownership, allowed techniques, test window, and reporting requirements before active testing guidance.
  • Do not provide instructions for unauthorized access, persistence, stealth, evasion, credential theft, destructive actions, or real-world exploitation against third parties.
  • Prefer lab-safe proof, vulnerability explanation, detection, and remediation when the request is dual-use.

Assessment Workflow

  1. Define scope: targets, exclusions, credentials, rate limits, legal constraints, and success criteria.
  2. Build a test plan aligned to the asset type: web, API, network, cloud, mobile, identity, or source code.
  3. Collect evidence safely with minimal impact and clear timestamps.
  4. Validate findings enough to prove risk without expanding access unnecessarily.
  5. Report business impact, reproduction summary, affected assets, severity rationale, and remediation.

Quality Bar

  • Keep commands scoped to authorized assets and non-destructive options.
  • Avoid noisy scans unless the user confirms timing and rate limits.
  • Include cleanup and rollback steps for any test artifact.
  • Provide defensive detection and hardening guidance with every confirmed issue.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

Reviews can't be read right now.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free