defensive-security-review
Skill6 starsChanged 42 days agoMITView on GitHub
In this repository36 other files it gives its agents.
- bioinformatics-planningSkill
- biology-literature-analysisSkill
- biology-paper-analysisSkill
- chemistry-research-analysisSkill
- skill-authorSkill
- codebase-explorerSkill
- codebase-understandingSkill
- code-reviewSkill
- debug-systematicallySkill
- implementation-plannerSkill
- implementation-reviewSkill
- ledger-tasks-yyloSkill
- test-and-verifySkill
- algorithm-learningSkill
- system-design-basicsSkill
- threat-modelingSkill
- data-analysisSkill
- tutorSkill
- experiment-analysisSkill
- model-evaluationSkill
- numerical-methodsSkill
- mathematics-problem-solverSkill
- proof-solvingSkill
- physics-research-analysisSkill
- data-cleaningSkill
- data-visualizationSkill
- evidence-checkerSkill
- evidence-comparisonSkill
- experimental-planningSkill
- literature-synthesizerSkill
- reproducibility-auditSkill
- research-questionSkill
- source-verificationSkill
- api-designSkill
- frontend-planningSkill
- technical-editorSkill
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
- Distinctive: line 13
Use when reviewing code, architecture, configuration, or a system you own or have explicit permission to assess.
- Distinctive: line 19
Validate proportionately: Prefer local tests, static analysis, and harmless proof-of-concept checks.
- Distinctive: line 37
Do not claim a vulnerability is confirmed without evidence.
≈ “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.
Files
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
- Confirm scope. Identify the authorized application, repository, environment, and excluded systems. If authorization or scope is unclear, ask before testing.
- Map assets and trust boundaries. Identify sensitive data, authentication, authorization, external inputs, privileged operations, and third-party dependencies.
- Inspect defensively first. Review source code, dependency manifests, configuration, access controls, error handling, logging, and secrets handling before considering active tests.
- 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.
- Prioritize findings. For each issue, record the affected component, preconditions, impact, evidence, severity rationale, and confidence. Separate confirmed defects from hypotheses.
- Recommend fixes. Give the smallest safe remediation, a regression test, and any relevant defense-in-depth measure.
- 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.
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
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.

