agentleFS
cellrishi-codecellrishi-code/claude-skills-atlas/skills/cybersecurity/defensive-security-review/SKILL.md

defensive-security-review

Skill6 starsChanged 42 days agoMITView on GitHub

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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 when reviewing code, architecture, configuration, or a system you own or have explicit permission to assess.

    line 13
  2. Distinctive:

    Validate proportionately: Prefer local tests, static analysis, and harmless proof-of-concept checks.

    line 19
  3. Distinctive:

    Do not claim a vulnerability is confirmed without evidence.

    line 37

≈ “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

Defensive Security Review

Purpose

Review an application or code change for security weaknesses and produce actionable, proportionate remediation guidance.

When to use

Use when reviewing code, architecture, configuration, or a system you own or have explicit permission to assess.

Instructions

  1. Confirm scope. Identify the authorized application, repository, environment, and excluded systems. If authorization or scope is unclear, ask before testing.
  2. Map assets and trust boundaries. Identify sensitive data, authentication, authorization, external inputs, privileged operations, and third-party dependencies.
  3. Inspect defensively first. Review source code, dependency manifests, configuration, access controls, error handling, logging, and secrets handling before considering active tests.
  4. Validate proportionately. Prefer local tests, static analysis, and harmless proof-of-concept checks. Do not access other users' data, disrupt availability, persist access, or extract secrets.
  5. Prioritize findings. For each issue, record the affected component, preconditions, impact, evidence, severity rationale, and confidence. Separate confirmed defects from hypotheses.
  6. Recommend fixes. Give the smallest safe remediation, a regression test, and any relevant defense-in-depth measure.
  7. Recheck. Explain how to verify the fix and what residual risk remains.

Inputs

  • Authorized scope and exclusions
  • Repository, architecture, or configuration under review
  • Relevant threat model and deployment context
  • Available test constraints

Outputs

A concise report with an executive summary, prioritized findings, reproducible non-destructive evidence, remediation steps, and verification tests.

Example

For an endpoint that accepts a user-supplied account ID, trace whether the server checks that the authenticated user owns that account. Recommend a server-side ownership check and tests for both authorized and unauthorized access.

Limitations

Do not claim a vulnerability is confirmed without evidence. Do not perform testing outside the agreed scope. This skill supports defensive review and does not replace a full professional assessment.

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.