blueteam-defend
Skill2 starsChanged 17 days agoNo licenceView on GitHub
Act as a defensive security engineer over a real, accessible codebase, driven by one doctrine — never trust the client. Systematically hunt for every place the backend blindly trusts attacker-controlled input (request bodies, IDs, headers, JWTs, uploads, forwarded identity) and the real vulnerabilities that follow: broken access control / IDOR / BOLA, mass assignment, injection, SSRF to cloud metadata, insecure deserialization, prototype pollution, crypto failures, supply-chain CVEs, misconfiguration, and fail-open error handling — mapped to OWASP Top 10 2025 and API Top 10 2023. Report each finding with exact `file:line` evidence, then propose and — only after the user approves — apply concrete fixes in place and verify them. Use this skill when the user says "security audit", "find vulnerabilities", "audit my code", "secure this codebase", "harden this", "make it unbreakable", "never trust user input", "find security bugs", "scan for vulns", "is this code safe", "check for security issues", "fix the security problems", or asks you to review their own project for security flaws and remediate them. This is the blue-team counterpart to redteam-attack: it operates on code it can read and edit, not just specs.
- Reads credentials
In this repository8 other files it gives its agents.
- 3d-website-guideSkill
- cf-fullstack-starterSkill
- dead-code-auditSkill
- frontend-designSkill
- human-writing-styleSkill
- redteam-attackSkill
- security-audit-orchestratorSkill
- theme-factorySkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
23 rules. About 0 are common, 15 are distinctive, and 8 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈15
Distinctive · estimate
This author's own choices. Worth a look.
8
Very specific
Tied to their project's names, files or tools. Probably skip.
No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “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.
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.