security-check
Skill1 starsChanged 2 months agoMITView on GitHub
Audit code against the OWASP Top 10 (injection, XSS, CSRF, auth and sessions, data exposure, misconfiguration, vulnerable dependencies, API security) and write a findings report with severity, location, proof of concept and fix. Args: [<path>]
30 other projects use a version of this.
Adopted by
Most recently taken up by
- cecewu3/agent-trading-skillstheir own version, first seen Nov 8, 2026
- simonasrazm/skillstheir own version, first seen Nov 8, 2026
- MagicJosh/rastheir own version, first seen Nov 2, 2026
- pablopetr/claude-skillstheir own version, first seen Oct 25, 2026
- aws-samples/sample-agentic-coding-harness-benchmarkstheir own version, first seen Oct 20, 2026
- Nirusan/claude-configtheir own version, first seen Oct 13, 2026
Used with
Projects with it also use code-review.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
GoogleSkillcode-review
Adversarial systems, concurrency, memory-model, and architecture code review protocol. Use this skill whenever asked to review code, PRs, diffs, or branches in Filament.
Also in 5 projects that use this
Other versions30 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 30
- alibaba/loongcollector★ 2.2ksame name
- gocronx-team/gocron★ 808same name
- TermiX-official/cryptoclaw★ 100same name
- igmarin/rails-agent-skills★ 26same name
- aws-samples/sample-agentic-coding-harness-benchmarks★ 20same name
- Benkapner/claude-code-basecamp★ 17same name
- YehudaFrankel/clankbrain★ 16same name
- DailybotHQ/deepworkplan-website★ 15same name
- Nirusan/claude-config★ 7same name
- brunobracaioli/business_dossie★ 4same name
20 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository17 other files it gives its agents.
- check-drySkill
- check-testsSkill
- create-commit-messageSkill
- create-unit-testsSkill
- deslop-proseSkill
- deslopSkill
- fanout-reviewSkill
- fix-security-auditSkill
- framework-upgrade-guideSkill
- generate-adrSkill
- learnSkill
- optimizeSkill
- pr-descriptionSkill
- resolve-merge-conflictsSkill
- ship-itSkill
- takeawaysSkill
- update-claude-mdSkill
The file
We split this skill into the rules it gives an agent
1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.
0
Common
Most of the 22 edited versions we read keep these.
1
Distinctive
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 28
Write the report in the language of the user's request.
“Common” is measured: kept by at least 6 in 10 of the 22 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
<!-- Note: $ARGUMENTS is substituted by Claude commands only. In Copilot,
the user must include their argument inline in the prompt; the skill
body sees the literal text "$ARGUMENTS" unsubstituted. -->Arguments
[<path>]
- Optional. A file or directory to scope the audit; omit to audit the whole project.
- Examples:
/security-check,/security-check src/api
Copilot CLI note:
$ARGUMENTSdoes not substitute in skills; include the argument inline in your prompt.
Security check: $ARGUMENTS
Audit the code against the OWASP Top 10 and report the findings. Read the relevant code (route handlers, authentication, database access, configuration, dependencies) before asserting anything: a finding without evidence in the code is noise and costs the trust of whoever has to fix it.
Language and style
Write the report in the language of the user's request. Use active voice, short sentences, one idea per paragraph, no decorative emoji, and explain why each risk matters, not only what it is. Keep code identifiers in backticks with their original spelling.
OWASP Top 10
- Injection: SQL, NoSQL, OS commands, LDAP, XPath
- Authentication and sessions: weak passwords, insecure credential storage, session fixation, missing session timeout
- XSS: reflected, stored, DOM-based, missing output encoding
- Insecure direct object reference (IDOR): unauthorized access, missing access controls
- Security misconfiguration: insecure defaults, unnecessary features enabled, missing security headers, verbose errors
- Sensitive data exposure: unencrypted data, weak encryption, leaks in logs or URLs
- CSRF: missing or weak CSRF tokens
- Vulnerable dependencies: outdated libraries, missing security patches
- Logging and monitoring: missing audit trails, inadequate error logging
- API security: missing rate limiting, weak authentication, excessive data exposure
Report
For each finding, give these fields:
- Severity: Critical / High / Medium / Low
- Location: affected file(s) and line(s)
- Proof of concept (when applicable)
- Remediation steps
Structure
- Executive summary of the security posture
- Critical and high findings (fix immediately)
- Medium and low findings (plan for upcoming sprints)
- Long-term security recommendations
At the end, if the report uses 5 or more technical acronyms, add a short glossary table with the meaning of each one. Omit the obvious ones (SQL, API) and keep the domain-specific ones (IDOR, CSRF).
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.