Home / security-basics

Security Basics

Seven lightweight security skills for everyday development: secrets hygiene scan, npm audit and pip-audit reader, HTTP security header check, JWT inspector, CORS review, auth flow review and a security review of a diff. Agent and MCP security lives in the agent-security-skills marketplace.

Plugin security-basics, version 0.4.1, 7 skills, MIT licence. Source: claude-dev-skills. Synced .

Install

In Claude Code, add the marketplace and install the plugin:

/plugin marketplace add basitalisandhu/claude-skills
/plugin install security-basics@claude-skills

Or copy the skill files into ~/.claude/skills/ from a clone:

git clone https://github.com/basitalisandhu/claude-skills
cd claude-skills
python3 install.py --user --only security-basics

Skills

SkillWhat it doesScripts
auth-flow-reviewFind the weaknesses in an application's whole sign-in, login and session design (passwords, sessions and cookies, OAuth and OIDC with PKCE, state and redirect URIs, MFA, password reset, account enumeration, rate limiting), then report findings by severity with the corrected flow.no
cors-reviewReview a CORS configuration (allowed origins, Access-Control-Allow-Origin with credentials, methods, headers, preflight caching, exposed headers) against the mistakes that leak data cross-site or break real clients, and write the correct config for Express, nginx or the gateway in use.no
dependency-audit-readerRead the JSON output of npm audit, yarn audit, pip-audit or cargo audit with a bundled script that ranks vulnerable packages by severity, separates fixable from unfixable and direct from transitive, and names the packages to upgrade first; then plan the upgrades, overrides and accepted risks with expiry dates.yes
diff-security-reviewReview a change for what it adds to the attack surface before it merges: a bundled script scans only the added lines of a saved git or gh diff for new network calls, shell and process execution, unsafe deserialisation, SQL built from strings, credential-shaped literals, disabled TLS checks and new permissions in workflows and manifests, with file and line.yes
http-security-headersGrade the security headers in a saved HTTP response (HSTS, CSP, nosniff, frame protection, Referrer-Policy, Permissions-Policy, cookie flags, disclosure, caching) with a bundled script, then write the header config for nginx, the server or the framework.yes
jwt-inspectorDecode a JWT or bearer access token without verifying it, with a bundled script that prints the header, claims and expiry, and flags unsafe settings (alg none, empty signature, long or missing expiry, jku or x5u, suspicious kid, HS256 and other symmetric algorithms, email or other sensitive claims in the payload); then check whether the token design is safe.yes
secrets-hygieneFind leaked credentials (cloud and SaaS keys, private keys, tokens, connection strings, high-entropy assignments) in a repository, directory or staged files with a bundled script that redacts them, check .env files are ignored, keep a baseline of accepted findings, and guide rotation and cleanup.yes

Plugin README

Seven lightweight security skills for everyday development: a secrets scan, an audit report reader, an HTTP security header check, a JWT inspector, a CORS review, an auth flow review and a security review of a diff. Agent and MCP security lives in the agent-security-skills marketplace.

Find this when you search for: OWASP Top 10, npm audit fix, security review of a pull request.

Install

/plugin marketplace add basitalisandhu/claude-dev-skills
/plugin install security-basics@claude-dev-skills

Skills then appear as /security-basics:<skill>. Scripts need Python 3.11 or newer on PATH as python3; they use the standard library only and make no network calls.

Skills

SkillTriggers onProduces
secrets-hygienecheck for secrets, pre-commit, after a leaksecrets_scan.py redacted findings, baseline, rotation steps
dependency-audit-readernpm audit or pip-audit fails CIaudit_reader.py ranked packages, upgrade and override plan
http-security-headersare our headers secure, scanner findingheaders_check.py grade and the server configuration
jwt-inspectorwhat is in this token, is our JWT setup safejwt_inspect.py decoded claims (unverified) and findings
cors-reviewCORS error, allow the frontend, permissive policychecklist findings and the allowlist configuration
auth-flow-reviewdesign login, review auth, account takeoverper-flow findings with severity and corrected flows
diff-security-reviewis this PR safe security-wise, pre-merge security passdiff_security_scan.py findings on added lines, read with the code around them

Tests for every script live in the repository's tests/ directory; run python3 -m pytest -q at the repository root.

Sample output

dependency-audit-reader on an npm audit --json report (npm 7 or later) with a direct, a transitive and an unfixable advisory:

$ python3 "${CLAUDE_PLUGIN_ROOT}/skills/dependency-audit-reader/scripts/audit_reader.py" audit.json
dependency-audit-reader 0.1.0: npm: 3 vulnerable packages critical=2, high=1; 2 fixable, 1 without a fix
severity  package                      installed        direct fix                      advisories
critical  minimist                     <0.2.4           no     no                       1097, GHSA-xvch-5gv4-984h  Prototype Pollution in minimist
critical  mkdirp                       0.4.1 - 0.5.1    yes    yes                      via minimist
high      lodash                       <4.17.21         yes    lodash@4.17.21           1096, GHSA-35jh-r3h4-6jhm  Command Injection in lodash
upgrade first: minimist, mkdirp, lodash
exit 1

--ignore GHSA-35jh-r3h4-6jhm (or the npm source number 1096) drops the lodash advisory; a package leaves the list only when every advisory on it is ignored.