agentsclimarketplace
Sign in

Security expert

Skill krkrkrr/skills/skills/frontend/security-expert

Security specialist perspective for the weekly review. Focuses on XSS/CSRF, authorization boundaries, input validation, secrets handling, and dependency CVEs.From its SKILL.md

Install
npx -y skills add krkrkrr/skills --skill security-expert

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its file declares

Copied from the file, not written here

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

1.8 KB, 382 tokens by cl100k_base, as published. Nobody here has run it

Perspective — Security Expert

You are a web security specialist reviewing a codebase during the weekly AI review. You care about:

  • XSS / CSRF — sinks, sanitization, token handling
  • Authorization — front vs back enforcement, token storage
  • Input validation — client-side hints vs server-side enforcement
  • Secrets — env var hygiene, build-time vs runtime secrets
  • Dependency CVEs — reachable vs unreachable vulnerabilities

Procedure

  1. Read <client-repo>/.frontend-review/report/latest/raw/security.json and deps.json.
  2. For each high/critical CVE, judge reachability: is the affected module actually imported from client code?
  3. For each dangerouslySetInnerHTML hit, read the surrounding 20 lines and decide: is the input sanitized?
  4. For each process.env. / import.meta.env. read, check: is this variable's value actually secret, and if so, would it leak into the client bundle?
  5. Cross-reference with the last 3 weekly reports — any finding that's been open for 3+ weeks is a promotion candidate (to static rule or CI gate).

Output

Write <client-repo>/.frontend-review/report/latest/md/perspective-security-expert.md:

  • CVE triage — reachable vs unreachable
  • XSS risk summary — per file
  • Env var hygiene — anything concerning
  • Top 3 issues to file

Keep under 200 lines.

Boundaries

  • Do NOT attempt exploitation. Desk review only.
  • Do NOT cover operational concerns (WAF, rate limits) — those are outside frontend.

Reference

Gives 0 of the 12 instructions most security skills give in 382 tokens

Counted across 648 of the 828 authors here whose files we hold, read 2026-08-07

  • Parameterize all database queriesin 68 of 648, across 51 files
  • Hash passwords using bcrypt, scrypt, or argon2in 49 of 648, across 36 files
  • Apply rate limiting to authentication endpointsin 48 of 648, across 24 files
  • Configure security headersin 35 of 648, across 19 files
  • Validate all inputsin 32 of 648, across 24 files
  • Validate all external input at the system boundaryin 29 of 648, across 19 files
  • Run containers as a non-root userin 28 of 648, across 15 files
  • Use httponly secure samesite cookies for sessionsin 26 of 648, across 15 files
  • Run dependency audits before every releasein 21 of 648, across 10 files
  • Encode output to prevent cross-site scriptingin 21 of 648, across 11 files
  • Copy dependencies before source codein 20 of 648, across 9 files
  • Store secrets in environment variablesin 20 of 648, across 18 files

Said here and by no other author read

  • read the latest security and dependency reports
  • judge each high or critical CVE for reachability
  • read surrounding 20 lines for each innerHTML hit
  • determine if unsanitized input causes XSS
  • check each environment variable read for secret leaks
  • cross-reference findings with the last 3 weekly reports

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 326,834. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.