agentleFS
Sign inStart free
XakkiXakki/ai-agents-skills/skills/security-boundary-review/SKILL.md

security-boundary-review

Skill6 starsChanged 3 months agoMITView on GitHub

Independently review a claimed security repair or boundary contract with adversarial tests and current evidence, read-only. Use for security acceptance. RU: приёмка безопасности.

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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:

    Use adversarial cases and credentials and artifact, recovery and integration evidence when relevant.

    line 14

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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

Security acceptance review

Use for an independent, read-only review of a claimed security repair or boundary contract. Freeze the authorized candidate and evidence scope, then map each claim to the real caller, trust boundary, forbidden effect and observable result. Protect unrelated work and secret or opaque data; use synthetic fixtures and approved runners.

Review the whole path, not only a helper: policy and authentication, resource authority, parsing, storage, runtime transport, output, cancellation and cleanup as applicable. A green broad suite does not override a reproduced defect, and an unavailable test is not a pass. Separate confirmed findings, fixture or environment blockers and untested claims.

Use adversarial cases and credentials and artifact, recovery and integration evidence when relevant. Report concrete location, trigger, observable impact and deciding evidence; do not edit, deploy, restart, access live credentials or force external calls under review-only authority.

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