Install
$ agentstack add skill-kriscard-skills-review ✓ scanned · ✓ verified, works with Claude Code, Cursor, and more.
Security review
✓ PassedNo issues found. Passed automated security review. · v0.1.0 How review works →
- ✓ Prompt-injection patterns
- ✓ Secret / credential exfiltration
- ✓ Dangerous shell & filesystem operations
- ✓ Untrusted network calls
- ✓ Known-malicious package signatures
What it can access
- ✓ Network access No
- ✓ Filesystem access No
- ✓ Shell / process execution No
- ✓ Environment & secrets No
- ✓ Dynamic code execution No
From automated source analysis of v0.1.0. “Used” means the capability is present in the source — more access means more to trust, not that it’s unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work →About
Code Review
Security, correctness, and production reliability — in that priority order.
Priority Order
- Security — SQL injection, XSS, CSRF, auth bypass, secrets in code, input validation
- Correctness — Logic errors, data loss risks, broken error handling, edge cases
- Performance — N+1 queries, memory leaks, blocking operations, missing indexes
- Maintainability — Complexity, duplication, unclear abstractions
- Style — Last, and only if it deviates from team conventions
Review Checklist
Security (block on any of these):
- [ ] No SQL injection vectors (parameterized queries used)
- [ ] No XSS — user input sanitized before rendering
- [ ] Auth checks on all sensitive operations
- [ ] No secrets or credentials in code
- [ ] Input validation at system boundaries
Correctness:
- [ ] Error paths handled — no silent failures
- [ ] Edge cases covered (empty, null, zero, large values)
- [ ] Async operations properly awaited
- [ ] No data mutation where immutability expected
Performance:
- [ ] No N+1 queries in loops
- [ ] Database queries have appropriate indexes
- [ ] No memory leaks (event listeners, timers cleaned up)
- [ ] Expensive operations cached where appropriate
Tests:
- [ ] Tests exist for new code
- [ ] Tests cover error paths, not just happy path
- [ ] No over-mocking that makes tests pass while real code breaks
Output Format
## Summary
[1-sentence overall assessment]
Issues: N critical · N high · N medium · N low
## 🔴 Critical (block)
1. `file:line` — [issue]
**Problem:** ...
**Fix:** ...
## 🟠 High (should fix)
...
## 🟡 Medium (suggestions)
...
## ✅ What's good
...
## Verdict
[Approve / Request Changes / Block]
What Not To Do
- Don't block on style preferences — that's what linters are for
- Don't give vague feedback like "this could be better"
- Don't approve without understanding the changes
- Don't ignore config changes — they cause most production incidents
References
| Priority | Load when | Reference | |----------|-----------|-----------| | 1 — High | Reviewing UI code, component APIs, accessibility, or web interface patterns | references/web-interface-guidelines.md |
Source & license
This open-source skill is cataloged on AgentStack and links to its original source — we do not rehost the code.
- Author: kriscard
- Source: kriscard/Skills
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.