agentleFS
Sign inStart free
AdarshukumarAdarshukumar/skills/.agents/skills/authorized-security-assessment/SKILL.md

authorized-security-assessment

Skill1 starsChanged 41 days agoMITView on GitHub

Plan and conduct bounded defensive security assessments only on systems the user owns or has explicit permission to test; require scope, safety limits, evidence, remediation, and stop conditions.

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:

    Before active network or application testing, obtain and record: target assets, ownership or written authorization, allowed techniques, …

    line 7
  2. Distinctive:

    Verify findings manually without extracting real data or causing persistence.

    line 14
  3. Distinctive:

    No unauthorized targets, destructive tests, denial of service, stealth/evasion, persistence, malware, credential theft, phishing, mass …

    line 17
  4. Distinctive:

    Stop on scope ambiguity, instability, unexpected sensitive data, possible third-party impact, rate-limit alarms, or instruction from the …

    line 19

≈ “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

Authorized Security Assessment

Mandatory gate

Before active network or application testing, obtain and record: target assets, ownership or written authorization, allowed techniques, excluded assets, testing window, source IPs, rate limits, data-handling rules, emergency contact, and stop conditions. If any are absent, use human-input and do not begin active testing.

Safe sequence

  1. Threat model and asset inventory.
  2. Passive repository/configuration review.
  3. Secrets, dependency, SAST, IaC, container, and SBOM scans.
  4. Staging-only DAST using conservative rate limits and non-destructive checks.
  5. Authentication/authorization tests with dedicated test accounts and synthetic data.
  6. Verify findings manually without extracting real data or causing persistence.
  7. Report evidence, severity, affected asset, safe reproduction summary, remediation, and retest result.

Prohibited

No unauthorized targets, destructive tests, denial of service, stealth/evasion, persistence, malware, credential theft, phishing, mass scanning, third-party pivoting, production data extraction, or bypassing provider safeguards.

Stop immediately

Stop on scope ambiguity, instability, unexpected sensitive data, possible third-party impact, rate-limit alarms, or instruction from the owner.

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.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

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