mcpField

security-review

github.com/icodecraftSecurity2745 installsUpdated 14w ago
Repository

About security-review

security-review is a code-change security review skill for reviewers. It focuses on diffs and related call paths, with a concrete checklist and severity-based findings format.

Key features

  1. 01Check authentication and authorization
  2. 02Review input handling and data safety
  3. 03Inspect secrets and configuration risks
  4. 04Check network and server security
  5. 05Review dangerous APIs and deserialization
  6. 06Group findings by severity with fixes

Use cases

  1. 01Review a code diff before merging
  2. 02Check access control for sensitive actions
  3. 03Find risks in input, uploads, and path handling

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/icodecraft/anti-slop --skill security-review

After installing, type/security-reviewin Claude Code to confirm it loaded.

Details

From the project README

Security Review

Review the current change like a security-minded senior. Prefer concrete findings over generic advice.

Scope

Focus on the diff and directly related call paths. Do not audit the whole repo unless asked.

Checklist

Auth & access
  • Every sensitive action checks authentication and authorization
  • IDs from the client are not trusted for ownership (userId in body ≠ proof)
  • Admin/debug routes are gated; no "temporary" open endpoints
Input & data
  • User input is validated at the boundary (type, length, allowlist)
  • SQL/NoSQL/search queries are parameterized — no string concat
  • HTML/Markdown/user content is escaped or sanitized where rendered
  • File uploads: size limits, type allowlist, stored outside web root, randomized names
  • Path joins cannot escape intended directories (../)
Secrets & config
  • No secrets in source, logs, client bundles, or example env files with real values
  • New env vars documented; defaults are safe for production
  • Tokens/passwords not written to analytics or error trackers
Network & server
  • Outbound fetches do not accept raw user URLs without allowlisting (SSRF)
  • CORS is least-privilege; credentials only when required
  • Cookies: HttpOnly, Secure, SameSite where applicable
Dangerous APIs
  • No eval, dangerouslySetInnerHTML, shell exec with unsanitized input
  • Deserialization of untrusted data is avoided or hardened
  • Crypto/auth libraries are standard — no home-rolled JWT/crypto

Output format

Group findings:

SeverityRuleWhereWhy it mattersFix
Critical / High / Medium / Low / Noteshort namefile:line or symbol1 sentenceconcrete change

End with:

  • Blockers — must fix before merge
  • Safe to ship with follow-ups — optional

If no issues: say so explicitly and list what you checked.

Comments

Markdown supported