Skip to content
Agentmart
Submit a tool

security-review

Review changed or existing code for authentication, authorization, input handling, injection, XSS, CSRF, SSRF, secret exposure, file upload, dependency, and…

Skill by PHENOMVALENCE

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/phenomvalence-security-review

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Review changed or existing code for authentication, authorization, input handling, injection, XSS, CSRF, SSRF, secret exposure, file upload, dependency, and business-logic risks.

Use cases: security

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/security-review

What's inside

Skill name
security-review
Description
Review changed or existing code for authentication, authorization, input handling, injection, XSS, CSRF, SSRF, secret exposure, file upload, dependency, and business-logic risks.
License
MIT
Instructions
20 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Security Review

## Workflow
1. Identify assets, trust boundaries, actors, and privileged operations.
2. Review authentication and session/token handling.
3. Verify authorization at every sensitive server-side action and object boundary.
4. Trace untrusted input into SQL, shell, templates, URLs, file paths, uploads, deserialization, and external requests.
5. Check output encoding, CSRF controls, CORS assumptions, rate limiting, and abuse cases.
6. Check secret handling, logs, error responses, configuration, and client bundles.
7. Review dependency additions and dangerous permissions.
8. Review payments/webhooks/idempotency/replay protections when relevant.
9. Prioritize findings by impact, exploitability, and evidence.
10. Fix verified issues and add regression coverage where practical.

## Rules
- Do not report speculative vulnerabilities as confirmed facts.
- Do not weaken validation, TLS, auth, or permission controls to simplify development.
- Never commit real secrets or customer data into tests/fixtures.

From PHENOMVALENCE/engineering-agent-skills, MIT.

More from PHENOMVALENCE/engineering-agent-skills

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Sep 16, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from PHENOMVALENCE

Cite this page

security-review skill. Agent Mart. https://agentmart.dev/skills/phenomvalence-security-review (last updated 2026-10-24)